You searched for subject:(Recurrent Neural Network).
Showing records 1 – 30 of
99 total matches.
◁ [1] [2] [3] [4] ▶
Penn State University
1.
Lin, Tao.
A DATA TRIAGE RETRIEVAL SYSTEM FOR CYBER SECURITY OPERATIONS CENTER.
Degree: 2018, Penn State University
URL: https://etda.libraries.psu.edu/catalog/14787txl78 
► Triage analysis is a fundamental stage in cyber operations in Security Operations Centers (SOCs). The massive data sources generate great demands on cyber security analysts'…
(more)
▼ Triage analysis is a fundamental stage in cyber operations in Security Operations Centers (SOCs). The massive data sources generate great demands on cyber security analysts' capability of information processing and analytical reasoning. Furthermore, most junior security analysts perform much less efficiently than senior analysts in deciding what data triage operations to perform. To help analysts perform better, retrieval methods need to be proposed to facilitate data triaging through retrieval of the relevant historical data triage operations of senior security analysts. This thesis conducts a research of retrieval methods based on
recurrent neural network, including rule-based retrieval and context-based retrieval of data triage operations. It further discusses the new directions in solving the data triage operation retrieval problem.The present situation is that most novice analysts who are responsible for performing data triage tasks suffer a great deal from the complexity and intensity of their tasks. To fill the gap, we propose to provide novice analysts with on-the-job suggestions by presenting the relevant data triage operations conducted by senior analysts in a previous task. A tracing method has been developed to track an analyst's data triage operations. This thesis mainly presents a data triage operation retrieval system that (1) models the context of a data triage analytic process, (2) uses
recurrent neural network to compare matching contexts, and (3) presents the matched traces to the novice analysts as suggestions. We have implemented and evaluated the performance of the system through both automated testing and human evaluation. The results show that the proposed retrieval system can effectively identify the relevant traces based on an analyst's current analytic process.
Advisors/Committee Members: Peng Liu, Thesis Advisor.
Subjects/Keywords: Recurrent Neural Network; Machine Learning; Retrieval; Security
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Lin, T. (2018). A DATA TRIAGE RETRIEVAL SYSTEM FOR CYBER SECURITY OPERATIONS CENTER. (Thesis). Penn State University. Retrieved from https://etda.libraries.psu.edu/catalog/14787txl78
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Lin, Tao. “A DATA TRIAGE RETRIEVAL SYSTEM FOR CYBER SECURITY OPERATIONS CENTER.” 2018. Thesis, Penn State University. Accessed November 18, 2019.
https://etda.libraries.psu.edu/catalog/14787txl78.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Lin, Tao. “A DATA TRIAGE RETRIEVAL SYSTEM FOR CYBER SECURITY OPERATIONS CENTER.” 2018. Web. 18 Nov 2019.
Vancouver:
Lin T. A DATA TRIAGE RETRIEVAL SYSTEM FOR CYBER SECURITY OPERATIONS CENTER. [Internet] [Thesis]. Penn State University; 2018. [cited 2019 Nov 18].
Available from: https://etda.libraries.psu.edu/catalog/14787txl78.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Lin T. A DATA TRIAGE RETRIEVAL SYSTEM FOR CYBER SECURITY OPERATIONS CENTER. [Thesis]. Penn State University; 2018. Available from: https://etda.libraries.psu.edu/catalog/14787txl78
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Mid Sweden University
2.
Wang, Xutao.
Chinese Text Classification Based On Deep Learning.
Degree: Information Systems and Technology, 2018, Mid Sweden University
URL: http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-35322
► Text classification has always been a concern in area of natural language processing, especially nowadays the data are getting massive due to the development…
(more)
▼ Text classification has always been a concern in area of natural language processing, especially nowadays the data are getting massive due to the development of internet. Recurrent neural network (RNN) is one of the most popular method for natural language processing due to its recurrent architecture which give it ability to process serialized information. In the meanwhile, Convolutional neural network (CNN) has shown its ability to extract features from visual imagery. This paper combine the advantages of RNN and CNN and proposed a model called BLSTM-C for Chinese text classification. BLSTM-C begins with a Bidirectional long short-term memory (BLSTM) layer which is an special kind of RNN to get a sequence output based on the past context and the future context. Then it feed this sequence to CNN layer which is utilized to extract features from the previous sequence. We evaluate BLSTM-C model on several tasks such as sentiment classification and category classification and the result shows our model’s remarkable performance on these text tasks.
Subjects/Keywords: Text classification; Recurrent neural network; Convolutional neural network; Computer Systems; Datorsystem
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Wang, X. (2018). Chinese Text Classification Based On Deep Learning. (Thesis). Mid Sweden University. Retrieved from http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-35322
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Wang, Xutao. “Chinese Text Classification Based On Deep Learning.” 2018. Thesis, Mid Sweden University. Accessed November 18, 2019.
http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-35322.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Wang, Xutao. “Chinese Text Classification Based On Deep Learning.” 2018. Web. 18 Nov 2019.
Vancouver:
Wang X. Chinese Text Classification Based On Deep Learning. [Internet] [Thesis]. Mid Sweden University; 2018. [cited 2019 Nov 18].
Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-35322.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Wang X. Chinese Text Classification Based On Deep Learning. [Thesis]. Mid Sweden University; 2018. Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-35322
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Mid Sweden University
3.
Guan, Xiao.
Deterministic and Flexible Parallel Latent Feature Models Learning Framework for Probabilistic Knowledge Graph.
Degree: Information Systems and Technology, 2018, Mid Sweden University
URL: http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-35788
► Knowledge Graph is a rising topic in the field of Artificial Intelligence. As the current trend of knowledge representation, Knowledge graph research is utilizing…
(more)
▼ Knowledge Graph is a rising topic in the field of Artificial Intelligence. As the current trend of knowledge representation, Knowledge graph research is utilizing the large knowledge base freely available on the internet. Knowledge graph also allows inspection, analysis, the reasoning of all knowledge in reality. To enable the ambitious idea of modeling the knowledge of the world, different theory and implementation emerges. Nowadays, we have the opportunity to use freely available information from Wikipedia and Wikidata. The thesis investigates and formulates a theory about learning from Knowledge Graph. The thesis researches probabilistic knowledge graph. It only focuses on a branch called latent feature models in learning probabilistic knowledge graph. These models aim to predict possible relationships of connected entities and relations. There are many models for such a task. The metrics and training process is detailed described and improved in the thesis work. The efficiency and correctness enable us to build a more complex model with confidence. The thesis also covers possible problems in finding and proposes future work.
Subjects/Keywords: Text classification; Recurrent neural network; Convolutional neural network; Computer Systems; Datorsystem
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Guan, X. (2018). Deterministic and Flexible Parallel Latent Feature Models Learning Framework for Probabilistic Knowledge Graph. (Thesis). Mid Sweden University. Retrieved from http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-35788
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Guan, Xiao. “Deterministic and Flexible Parallel Latent Feature Models Learning Framework for Probabilistic Knowledge Graph.” 2018. Thesis, Mid Sweden University. Accessed November 18, 2019.
http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-35788.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Guan, Xiao. “Deterministic and Flexible Parallel Latent Feature Models Learning Framework for Probabilistic Knowledge Graph.” 2018. Web. 18 Nov 2019.
Vancouver:
Guan X. Deterministic and Flexible Parallel Latent Feature Models Learning Framework for Probabilistic Knowledge Graph. [Internet] [Thesis]. Mid Sweden University; 2018. [cited 2019 Nov 18].
Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-35788.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Guan X. Deterministic and Flexible Parallel Latent Feature Models Learning Framework for Probabilistic Knowledge Graph. [Thesis]. Mid Sweden University; 2018. Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-35788
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Rochester Institute of Technology
4.
Nguyen, Thang Huy.
Automatic Video Captioning using Deep Neural Network.
Degree: MS, Computer Engineering, 2017, Rochester Institute of Technology
URL: https://scholarworks.rit.edu/theses/9516
► Video understanding has become increasingly important as surveillance, social, and informational videos weave themselves into our everyday lives. Video captioning offers a simple way…
(more)
▼ Video understanding has become increasingly important as surveillance, social, and informational videos weave themselves into our everyday lives. Video captioning offers a simple way to summarize, index, and search the data. Most video captioning models utilize a video encoder and captioning decoder framework. Hierarchical encoders can abstractly capture clip level temporal features to represent a video, but the clips are at fixed time steps. This thesis research introduces two models: a hierarchical model with steered captioning, and a Multi-stream Hierarchical Boundary model. The steered captioning model is the first attention model to smartly guide an attention model to appropriate locations in a video by using visual attributes. The Multi-stream Hierarchical Boundary model combines a fixed hierarchy
recurrent architecture with a soft hierarchy layer by using intrinsic feature boundary cuts within a video to define clips. This thesis also introduces a novel parametric Gaussian attention which removes the restriction of soft attention techniques which require fixed length video streams. By carefully incorporating Gaussian attention in designated layers, the proposed models demonstrate state-of-the-art video captioning results on recent datasets.
Advisors/Committee Members: Raymond Ptucha, Nathan Cahill, Dhireesha Kudithipudi.
Subjects/Keywords: Convolutional neural network; Deep learning; Recurrent neural network; Video captioning
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Nguyen, T. H. (2017). Automatic Video Captioning using Deep Neural Network. (Masters Thesis). Rochester Institute of Technology. Retrieved from https://scholarworks.rit.edu/theses/9516
Chicago Manual of Style (16th Edition):
Nguyen, Thang Huy. “Automatic Video Captioning using Deep Neural Network.” 2017. Masters Thesis, Rochester Institute of Technology. Accessed November 18, 2019.
https://scholarworks.rit.edu/theses/9516.
MLA Handbook (7th Edition):
Nguyen, Thang Huy. “Automatic Video Captioning using Deep Neural Network.” 2017. Web. 18 Nov 2019.
Vancouver:
Nguyen TH. Automatic Video Captioning using Deep Neural Network. [Internet] [Masters thesis]. Rochester Institute of Technology; 2017. [cited 2019 Nov 18].
Available from: https://scholarworks.rit.edu/theses/9516.
Council of Science Editors:
Nguyen TH. Automatic Video Captioning using Deep Neural Network. [Masters Thesis]. Rochester Institute of Technology; 2017. Available from: https://scholarworks.rit.edu/theses/9516
5.
Bidgoli, Rohollah Soltani.
Higher Order Recurrent Neural Network for Language Modeling.
Degree: MSc -MS, Computer Science, 2016, York University
URL: http://hdl.handle.net/10315/32337
► In this thesis, we study novel neural network structures to better model long term dependency in sequential data. We propose to use more memory units…
(more)
▼ In this thesis, we study novel
neural network structures to better model long term dependency in sequential data.
We propose to use more memory units to keep track of more preceding states in
recurrent neural networks (RNNs), which are all recurrently fed to the hidden layers as feedback through different weighted paths. By extending the popular
recurrent structure in RNNs, we provide the models with better short-term memory mechanism to learn long term dependency in sequences. Analogous to digital filters in signal processing, we call these structures as higher order RNNs (HORNNs). Similar to RNNs, HORNNs can also be learned using the back-propagation through time method. HORNNs are generally applicable to a variety of sequence modelling tasks. In this work, we have examined HORNNs for the language modeling task using two popular data sets, namely the Penn Treebank (PTB) and English text8 data sets. Experimental results have shown that the proposed HORNNs yield the state-of-the-art performance on both data sets, significantly outperforming the regular RNNs as well as the popular LSTMs.
Advisors/Committee Members: Jiang, Hui (advisor).
Subjects/Keywords: Computer science; Machine Learning; Deep Learning; Neural Network; Recurrent Neural Network; Language Modeling; Higher Order Recurrent Neural Network
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Bidgoli, R. S. (2016). Higher Order Recurrent Neural Network for Language Modeling. (Masters Thesis). York University. Retrieved from http://hdl.handle.net/10315/32337
Chicago Manual of Style (16th Edition):
Bidgoli, Rohollah Soltani. “Higher Order Recurrent Neural Network for Language Modeling.” 2016. Masters Thesis, York University. Accessed November 18, 2019.
http://hdl.handle.net/10315/32337.
MLA Handbook (7th Edition):
Bidgoli, Rohollah Soltani. “Higher Order Recurrent Neural Network for Language Modeling.” 2016. Web. 18 Nov 2019.
Vancouver:
Bidgoli RS. Higher Order Recurrent Neural Network for Language Modeling. [Internet] [Masters thesis]. York University; 2016. [cited 2019 Nov 18].
Available from: http://hdl.handle.net/10315/32337.
Council of Science Editors:
Bidgoli RS. Higher Order Recurrent Neural Network for Language Modeling. [Masters Thesis]. York University; 2016. Available from: http://hdl.handle.net/10315/32337
Tampere University
6.
Zhou, Yi.
Sentiment classification with deep neural networks
.
Degree: 2019, Tampere University
URL: https://trepo.tuni.fi//handle/10024/116148
► Sentiment classification is an important task in Natural Language Processing (NLP) area. Deep neural networks become the mainstream method to perform the text sentiment classification…
(more)
▼ Sentiment classification is an important task in Natural Language Processing (NLP) area. Deep neural networks become the mainstream method to perform the text sentiment classification nowadays. In this thesis two datasets are used. The first dataset is a hotel review dataset(TripAdvisor dataset) that collects the hotel reviews from the TripAdvisor website using Python Scrapy framework. The preprocessing steps are then applied to clean the dataset. A record in the TripAdvisor dataset consists of the text review and corresponding sentiment score. There are 5 sentimental labels: very negative, negative, neutral, positive, and very positive. The second dataset is the Stanford Sentiment Treebank (SST) dataset. It is a public and common dataset for sentiment classification.
Text Convolutional Neural Network (Text-CNN), Very Deep Convolutional Neural Network (VDCNN), and Bidirectional Long Short Term Memory neural network (BiLSTM) were chosen as different methods for the evaluation in the experiments. The Text-CNN was the first work to apply convolutional neural network architecture for the text classification. The VD-CNN applied deep convolutional layers, with up to 29 layers, to perform the text classification. The BiLSTM exploited the bidirectional recurrent neural network with long short term memory cell mechanism. On the other hand, word embedding techniques are also considered as an important factor in sentiment classification. Thus, in this thesis, GloVe and FastText techniques were used to investigate the effect of word embedding initialization on the dataset. GloVe is a unsupervised word embedding learning algorithm. FastText uses shallow neural network to generate word vectors and it has fast convergence speed for training and high speed for inference.
The experiment was implemented using PyTorch framework. It shows that the BiLSTM with GloVe as the word vector initialization achieved the highest accuracy 73.73% while the VD-CNN with FastText had the lowest accuracy 71.95% on the TripAdvisor dataset. The BiLSTM model achieved 0.68 F1-score while the VD-CNN model obtained 0.67 F1-score on the TripAdvisor dataset. On the SST dataset, BiLSTM with GloVe again achieved the highest accuracy 36.35% and 0.35 F1-score. The VD-CNN model with GloVe had the worst evaluation result in terms of accuracy and F1-score. The Text-CNN model performed better than the VD-CNN model even thought the VD-CNN model has more layers in most cases.
By analyzing the misclassified reviews in the TripAdvisor dataset from the three deep neural networks, it is shown that the hotel reviews with more contradictory sentimental words were more prone to misclassification than other hotel reviews.
Subjects/Keywords: deep neural networks;
convolutional neural network;
recurrent neural network;
sentiment classification;
hotel reviews;
TripAdvisor
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Zhou, Y. (2019). Sentiment classification with deep neural networks
. (Masters Thesis). Tampere University. Retrieved from https://trepo.tuni.fi//handle/10024/116148
Chicago Manual of Style (16th Edition):
Zhou, Yi. “Sentiment classification with deep neural networks
.” 2019. Masters Thesis, Tampere University. Accessed November 18, 2019.
https://trepo.tuni.fi//handle/10024/116148.
MLA Handbook (7th Edition):
Zhou, Yi. “Sentiment classification with deep neural networks
.” 2019. Web. 18 Nov 2019.
Vancouver:
Zhou Y. Sentiment classification with deep neural networks
. [Internet] [Masters thesis]. Tampere University; 2019. [cited 2019 Nov 18].
Available from: https://trepo.tuni.fi//handle/10024/116148.
Council of Science Editors:
Zhou Y. Sentiment classification with deep neural networks
. [Masters Thesis]. Tampere University; 2019. Available from: https://trepo.tuni.fi//handle/10024/116148
University of Illinois – Urbana-Champaign
7.
Yan, Zhicheng.
Image recognition, semantic segmentation and photo adjustment using deep neural networks.
Degree: PhD, Computer Science, 2016, University of Illinois – Urbana-Champaign
URL: http://hdl.handle.net/2142/90724
► Deep Neural Networks (DNNs) have proven to be effective models for solving various problems in computer vision. Multi-Layer Perceptron Networks, Convolutional Neural Networks and Recurrent…
(more)
▼ Deep
Neural Networks (DNNs) have proven to be effective models for solving various problems in computer vision. Multi-Layer Perceptron Networks, Convolutional
Neural Networks and
Recurrent Neural Networks are representative examples of DNNs in the setting of supervised learning. The key ingredients in the successful development of DNN-based models include but not limited to task-specific designs of
network architecture, discriminative feature representation learning and scalable training algorithms.
In this thesis, we describe a collection of DNN-based models to address three challenging computer vision tasks, namely large-scale visual recognition, image semantic segmentation and automatic photo adjustment. For each task, the
network architecture is carefully designed on the basis of the nature of the task. For large-scale visual recognition, we design a hierarchical Convolutional
Neural Network to fully exploit a semantic hierarchy among visual categories. The resulting model can be deemed as an ensemble of specialized classifiers. We improve state-of-the-art results at an affordable increase of the computational cost. For image semantic segmentation, we integrate convolutional layers with novel spatially
recurrent layers for incorporating global contexts into the prediction process. The resulting hybrid
network is capable of learning improved feature representations, which lead to more accurate region recognition and boundary localization. Combined with a post-processing step involving a fully-connected conditional random field, our hybrid
network achieves new state-of-the-art results on a large benchmark dataset. For automatic photo adjustment, we take a data-driven approach to learn the underlying color transforms from manually enhanced examples. We formulate the learning problem as a regression task, which can be approached with a Multi-Layer Perceptron
network. We concatenate global contextual features, local contextual features as well as pixel-wise features and feed them into the deep
network. State-of-the-art results are achieved on datasets with both global and local stylized adjustments.
Advisors/Committee Members: Yu, Yizhou (advisor), Lazebnik, Svetlana (Committee Chair), Forsyth, David (committee member), Cao, Liangliang (committee member).
Subjects/Keywords: Deep Neural Network; Image Recognition; Semantic Segmentation; Photo Adjustment; Convolutional Neural Network; Recurrent Neural Network; Multi-Layer Perceptron Network
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Yan, Z. (2016). Image recognition, semantic segmentation and photo adjustment using deep neural networks. (Doctoral Dissertation). University of Illinois – Urbana-Champaign. Retrieved from http://hdl.handle.net/2142/90724
Chicago Manual of Style (16th Edition):
Yan, Zhicheng. “Image recognition, semantic segmentation and photo adjustment using deep neural networks.” 2016. Doctoral Dissertation, University of Illinois – Urbana-Champaign. Accessed November 18, 2019.
http://hdl.handle.net/2142/90724.
MLA Handbook (7th Edition):
Yan, Zhicheng. “Image recognition, semantic segmentation and photo adjustment using deep neural networks.” 2016. Web. 18 Nov 2019.
Vancouver:
Yan Z. Image recognition, semantic segmentation and photo adjustment using deep neural networks. [Internet] [Doctoral dissertation]. University of Illinois – Urbana-Champaign; 2016. [cited 2019 Nov 18].
Available from: http://hdl.handle.net/2142/90724.
Council of Science Editors:
Yan Z. Image recognition, semantic segmentation and photo adjustment using deep neural networks. [Doctoral Dissertation]. University of Illinois – Urbana-Champaign; 2016. Available from: http://hdl.handle.net/2142/90724
Carnegie Mellon University
8.
Le, Ngan Thi Hoang.
Contextual Recurrent Level Set Networks and Recurrent Residual Networks for Semantic Labeling.
Degree: 2018, Carnegie Mellon University
URL: http://repository.cmu.edu/dissertations/1166
► Semantic labeling is becoming more and more popular among researchers in computer vision and machine learning. Many applications, such as autonomous driving, tracking, indoor navigation,…
(more)
▼ Semantic labeling is becoming more and more popular among researchers in computer vision and machine learning. Many applications, such as autonomous driving, tracking, indoor navigation, augmented reality systems, semantic searching, medical imaging are on the rise, requiring more accurate and efficient segmentation mechanisms. In recent years, deep learning approaches based on Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) have dramatically emerged as the dominant paradigm for solving many problems in computer vision and machine learning. The main focus of this thesis is to investigate robust approaches that can tackle the challenging semantic labeling tasks including semantic instance segmentation and scene understanding. In the first approach, we convert the classic variational Level Set method to a learnable deep framework by proposing a novel definition of contour evolution named Recurrent Level Set (RLS). The proposed RLS employs Gated Recurrent Units to solve the energy minimization of a variational Level Set functional. The curve deformation processes in RLS is formulated as a hidden state evolution procedure and is updated by minimizing an energy functional composed of fitting forces and contour length. We show that by sharing the convolutional features in a fully end-to-end trainable framework, RLS is able to be extended to Contextual Recurrent Level Set (CRLS) Networks to address semantic segmentation in the wild problem. The experimental results have shown that our proposed RLS improves both computational time and segmentation accuracy against the classic variational Level Set-based methods whereas the fully end-to-end system CRLS achieves competitive performance compared to the state-of-the-art semantic segmentation approaches on PAS CAL VOC 2012 and MS COCO 2014 databases. The second proposed approach, Contextual Recurrent Residual Networks (CRRN), inherits all the merits of sequence learning information and residual learning in order to simultaneously model long-range contextual infor- mation and learn powerful visual representation within a single deep network. Our proposed CRRN deep network consists of three parts corresponding to sequential input data, sequential output data and hidden state as in a recurrent network. Each unit in hidden state is designed as a combination of two components: a context-based component via sequence learning and a visualbased component via residual learning. That means, each hidden unit in our proposed CRRN simultaneously (1) learns long-range contextual dependencies via a context-based component. The relationship between the current unit and the previous units is performed as sequential information under an undirected cyclic graph (UCG) and (2) provides powerful encoded visual representation via residual component which contains blocks of convolution and/or batch normalization layers equipped with an identity skip connection. Furthermore, unlike previous scene labeling approaches [1, 2, 3], our method is not only able to exploit the…
Subjects/Keywords: Gated Recurrent Unit; Level Set; Recurrent Neural Networks; Residual Network; Scene Labeling; Semantic Instance Segmentation
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Le, N. T. H. (2018). Contextual Recurrent Level Set Networks and Recurrent Residual Networks for Semantic Labeling. (Thesis). Carnegie Mellon University. Retrieved from http://repository.cmu.edu/dissertations/1166
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Le, Ngan Thi Hoang. “Contextual Recurrent Level Set Networks and Recurrent Residual Networks for Semantic Labeling.” 2018. Thesis, Carnegie Mellon University. Accessed November 18, 2019.
http://repository.cmu.edu/dissertations/1166.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Le, Ngan Thi Hoang. “Contextual Recurrent Level Set Networks and Recurrent Residual Networks for Semantic Labeling.” 2018. Web. 18 Nov 2019.
Vancouver:
Le NTH. Contextual Recurrent Level Set Networks and Recurrent Residual Networks for Semantic Labeling. [Internet] [Thesis]. Carnegie Mellon University; 2018. [cited 2019 Nov 18].
Available from: http://repository.cmu.edu/dissertations/1166.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Le NTH. Contextual Recurrent Level Set Networks and Recurrent Residual Networks for Semantic Labeling. [Thesis]. Carnegie Mellon University; 2018. Available from: http://repository.cmu.edu/dissertations/1166
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
University of Miami
9.
Xie, Ziqian.
Deep Learning Approach for Brain Machine Interface.
Degree: PhD, Biomedical Engineering (Engineering), 2018, University of Miami
URL: https://scholarlyrepository.miami.edu/oa_dissertations/2096
► Objective: Brain machine interface (BMI) or Brain Computer Interface (BCI) provides a direct pathway between the brain and an external device to help people suffering…
(more)
▼ Objective: Brain machine interface (BMI) or Brain Computer Interface (BCI) provides a direct pathway between the brain and an external device to help people suffering from severely impaired motor function by decoding brain activities and translating human intentions into control signals. Conventionally, the decoding pipeline for BMIs consists of chained different stages of feature extraction, time-frequency analysis and statistical learning models. Each of these stages uses a different algorithm trained in a sequential manner, which makes the whole system difficult to be adaptive. Our goal is to create differentiable signal processing modules and plug them together to build an adaptive online system. The system could be trained with a single objective function and a single learning algorithm so that each component can be updated in parallel to increase the performance in a robust manner. We use deep
neural networks to address these needs. Main Results: We predicted the finger trajectory using Electrocorticography (ECoG) signals and compared results for the Least Angle Regression (LARS), Convolutional Long Short Term Memory
Network (Conv-LSTM), Random Forest (RF), and a pipeline consisting of band-pass filtering, energy extraction, feature selection and linear regression. The results showed that the deep learning models performed better than the commonly used linear model. The deep learning models not only gave smoother and more realistic trajectories but also learned the transition between movement and rest state. We also estimated the source connectivity of the brain signals using a
Recurrent Neural Network (RNN) and it correctly estimated the order and sparsity level of the underlying Multivariate Auto-regressive process (MVAR). The time course of the source connectivity was also recovered. Significance: We replace the conventional signal processing pipeline with differentiable modules so that the whole BMI system is adaptive. The study of the decoding system demonstrated a model for BMI that involved a convolutional and
recurrent neural network. It integrated the feature extraction pipeline into the convolution and pooling layer and used Long Short Term Memory (LSTM) layer to capture the state transitions. The decoding
network eliminated the need to separately train the model at each step in the decoding pipeline. The whole system can be jointly optimized using stochastic gradient descent and is capable of online learning. The study of the source connectivity estimation demonstrated a generative RNN model that can estimate the un-mixing matrix and the MVAR coefficients of the source activity at the same time. Our method addressed the issue of estimation and inference of the non-stationary MVAR coefficients and the un-mixing matrix in the presence of non-gaussian noise. More importantly, this model can be easily plugged into the BMI decoding system as a differentiable feature extraction module.
Advisors/Committee Members: Abhishek Prasad, Odelia Schwartz, Jorge Bohórquez, Suhrud M. Rajguru, Ozcan Ozdamar.
Subjects/Keywords: brain machine interface; signal processing; recurrent neural network; convolutional neural network; trajectory decoding; connectivity analysis
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Xie, Z. (2018). Deep Learning Approach for Brain Machine Interface. (Doctoral Dissertation). University of Miami. Retrieved from https://scholarlyrepository.miami.edu/oa_dissertations/2096
Chicago Manual of Style (16th Edition):
Xie, Ziqian. “Deep Learning Approach for Brain Machine Interface.” 2018. Doctoral Dissertation, University of Miami. Accessed November 18, 2019.
https://scholarlyrepository.miami.edu/oa_dissertations/2096.
MLA Handbook (7th Edition):
Xie, Ziqian. “Deep Learning Approach for Brain Machine Interface.” 2018. Web. 18 Nov 2019.
Vancouver:
Xie Z. Deep Learning Approach for Brain Machine Interface. [Internet] [Doctoral dissertation]. University of Miami; 2018. [cited 2019 Nov 18].
Available from: https://scholarlyrepository.miami.edu/oa_dissertations/2096.
Council of Science Editors:
Xie Z. Deep Learning Approach for Brain Machine Interface. [Doctoral Dissertation]. University of Miami; 2018. Available from: https://scholarlyrepository.miami.edu/oa_dissertations/2096
University of California – Berkeley
10.
Thanapirom, Chayut.
Neural Representation Learning with Denoising Autoencoder Framework.
Degree: Physics, 2016, University of California – Berkeley
URL: http://www.escholarship.org/uc/item/0hm6p6s5
► Understanding of how the brain works and how it can solve difficult problems like image recognition is very important, especially for the progress in developing…
(more)
▼ Understanding of how the brain works and how it can solve difficult problems like image recognition is very important, especially for the progress in developing an autonomous intelligent system. Even though we have a lot of experimental data in neuroscience, we are lack of theories which can glue all the observations together. One approach to understand the brain is to investigate the representation of sensory information in the brain at each stage, and try explains it with some computational level principle, for example an efficient coding principle. This thesis follows this approach.In this thesis, I use the denoising autoencoder framework to approach two unsolved problems in Computational Neuroscience. The first problem is learning the group structure in the group sparse coding model. I propose that it is possible to learn the group structure using gradient descent with a data denoising objective function. To verify the method, I train a model on the van Hateren's natural image dataset. The model with the learned group structure shows an improvement in denoising performance 15% (SNR) over the regular sparse coding model. Moreover, the group structure learned groups together sparse coding basis functions with similar location, orientation and scale.The second problem is to understand why we have grid cells. I proposed that a population of place cells and grid cells should be modeled as an attractor network with noisy neurons. Furthermore, this attractor network can be trained with the denoising autoencoder framework to memorized a location in 1D space (simplification of the actual problem where the location is in 2D space). I show that the retrieved location accuracy of the network with both place cells and grid cells is higher than the network with place cells alone. The performance difference is due to the activity of the grid cells acts as an efficient error-correcting code.
Subjects/Keywords: Biophysics; Neurosciences; Attractor Network; Denoising Autoencoder; Grid Cells; Neural Representation; Recurrent Neural Network; Sparse Coding
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Thanapirom, C. (2016). Neural Representation Learning with Denoising Autoencoder Framework. (Thesis). University of California – Berkeley. Retrieved from http://www.escholarship.org/uc/item/0hm6p6s5
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Thanapirom, Chayut. “Neural Representation Learning with Denoising Autoencoder Framework.” 2016. Thesis, University of California – Berkeley. Accessed November 18, 2019.
http://www.escholarship.org/uc/item/0hm6p6s5.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Thanapirom, Chayut. “Neural Representation Learning with Denoising Autoencoder Framework.” 2016. Web. 18 Nov 2019.
Vancouver:
Thanapirom C. Neural Representation Learning with Denoising Autoencoder Framework. [Internet] [Thesis]. University of California – Berkeley; 2016. [cited 2019 Nov 18].
Available from: http://www.escholarship.org/uc/item/0hm6p6s5.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Thanapirom C. Neural Representation Learning with Denoising Autoencoder Framework. [Thesis]. University of California – Berkeley; 2016. Available from: http://www.escholarship.org/uc/item/0hm6p6s5
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
University of Bridgeport
11.
Hassan, Abdalraouf.
Deep Neural Language Model for Text Classification Based on Convolutional and Recurrent Neural Networks
.
Degree: 2018, University of Bridgeport
URL: https://scholarworks.bridgeport.edu/xmlui/handle/123456789/2274
► The evolution of the social media and the e-commerce sites produces a massive amount of unstructured text data on the internet. Thus, there is a…
(more)
▼ The evolution of the social media and the e-commerce sites produces a massive amount of unstructured text data on the internet. Thus, there is a high demand to develop an intelligent model to process it and extract a useful information from it. Text classification plays an important task for many Natural Language Processing (NLP) applications such as, sentiment analysis, web search, spam filtering, and information retrieval, in which we need to assign single or multiple predefined categories to a sequence of text. In Neural Network Language Models learning long-term dependencies with gradient descent is difficult due to the vanishing gradient problem. Recently researchers started to increase the depth of the network in order to overcome the limitations of the existing techniques. However, increasing the depth of the network means increasing the number of the parameters, which makes the network computationally expensive, and more prone to overfitting. Furthermore, NLP systems traditionally treat words as discrete atomic symbols; the model can leverage small amounts of information regarding the relationship between the individual symbols. In recent years, deep learning models such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) have been applied to language modeling with comparative, remarkable results. CNNs are a noble approach to extract higher-level features invariant to local translation. However, this method requires the stacking of multiple convolutional layers in order to capture long-term dependencies because of the locality of the convolutional and pooling layers. In this dissertation, we introduce a joint CNN-RNN framework to overcome the problems in the existing deep learning models. Briefly, we applied an unsupervised neural language model to train initial word embeddings that are further tuned by our deep learning network, then the pre-trained parameters of the network are used to initialize the model. At a final stage, the proposed framework combines former information with a set of feature maps learned by a convolutional layer with long-term dependencies learned via Long-Short-Term Memory (LSTM). Empirically, we show that our approach, with slight hyperparameter tuning and static vectors, achieves outstanding results on multiple sentiment analysis benchmarks. Our approach outperforms several existing approaches in term of accuracy; our results are also competitive with the state-of-the-art results on the Stanford Large Movie Review (IMDB) dataset, and the Stanford Sentiment Treebank (SSTb) dataset. Our approach has a significant role in reducing the number of parameters and constructing the convolutional layer followed by the recurrent layer with no pooling layers. Our results show that we were able to reduce the loss of detailed, local information and capture long-term dependencies with an efficient framework that has fewer parameters and a high level of performance.
Subjects/Keywords: Convolutional neural network;
Deep learning;
Machine learning;
Natural language processing;
Recurrent neural network;
Sentiment analysis
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Hassan, A. (2018). Deep Neural Language Model for Text Classification Based on Convolutional and Recurrent Neural Networks
. (Thesis). University of Bridgeport. Retrieved from https://scholarworks.bridgeport.edu/xmlui/handle/123456789/2274
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Hassan, Abdalraouf. “Deep Neural Language Model for Text Classification Based on Convolutional and Recurrent Neural Networks
.” 2018. Thesis, University of Bridgeport. Accessed November 18, 2019.
https://scholarworks.bridgeport.edu/xmlui/handle/123456789/2274.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Hassan, Abdalraouf. “Deep Neural Language Model for Text Classification Based on Convolutional and Recurrent Neural Networks
.” 2018. Web. 18 Nov 2019.
Vancouver:
Hassan A. Deep Neural Language Model for Text Classification Based on Convolutional and Recurrent Neural Networks
. [Internet] [Thesis]. University of Bridgeport; 2018. [cited 2019 Nov 18].
Available from: https://scholarworks.bridgeport.edu/xmlui/handle/123456789/2274.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Hassan A. Deep Neural Language Model for Text Classification Based on Convolutional and Recurrent Neural Networks
. [Thesis]. University of Bridgeport; 2018. Available from: https://scholarworks.bridgeport.edu/xmlui/handle/123456789/2274
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Clemson University
12.
Wang, Xiaoyu.
ARCHITECTURE OPTIMIZATION, TRAINING CONVERGENCE AND NETWORK ESTIMATION ROBUSTNESS OF A FULLY CONNECTED RECURRENT NEURAL NETWORK.
Degree: PhD, Mechanical Engineering, 2010, Clemson University
URL: https://tigerprints.clemson.edu/all_dissertations/536
► Recurrent neural networks (RNN) have been rapidly developed in recent years. Applications of RNN can be found in system identification, optimization, image processing, pattern reorganization,…
(more)
▼ Recurrent neural networks (RNN) have been rapidly developed in recent years. Applications of RNN can be found in system identification, optimization, image processing, pattern reorganization, classification, clustering, memory association, etc. In this study, an optimized RNN is proposed to model nonlinear dynamical systems. A fully connected RNN is developed first which is modified from a fully forward connected
neural network (FFCNN) by accommodating
recurrent connections among its hidden neurons. In addition, a destructive structure optimization algorithm is applied and the extended Kalman filter (EKF) is adopted as a
network's training algorithm. These two algorithms can seamlessly work together to generate the optimized RNN. The enhancement of the modeling performance of the optimized
network comes from three parts: 1) its prototype - the FFCNN has advantages over multilayer perceptron
network (MLP), the most widely used
network, in terms of modeling accuracy and generalization ability; 2) the recurrency in RNN
network make it more capable of modeling non-linear dynamical systems; and 3) the structure optimization algorithm further improves RNN's modeling performance in generalization ability and robustness. Performance studies of the proposed
network are highlighted in training convergence and robustness. For the training convergence study, the Lyapunov method is used to adapt some training parameters to guarantee the training convergence, while the maximum likelihood method is used to estimate some other parameters to accelerate the training process. In addition, robustness analysis is conducted to develop a robustness measure considering uncertainties propagation through RNN via unscented transform. Two case studies, the modeling of a benchmark non-linear dynamical system and a tool wear progression in hard turning, are carried out to testify the development in this dissertation. The work detailed in this dissertation focuses on the creation of: (1) a new method to prove/guarantee the training convergence of RNN, and (2) a new method to quantify the robustness of RNN using uncertainty propagation analysis. With the proposed study, RNN and related algorithms are developed to model nonlinear dynamical system which can benefit modeling applications such as the condition monitoring studies in terms of robustness and accuracy in the future.
Advisors/Committee Members: Huang, Yong, Gowdy , John, Jalili , Nader, Vahidi , Ardalan.
Subjects/Keywords: Network Optimization; Network Robustness; Recurrent Neural Network; Training Algorithm; Training Convergence; Artificial Intelligence and Robotics
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Wang, X. (2010). ARCHITECTURE OPTIMIZATION, TRAINING CONVERGENCE AND NETWORK ESTIMATION ROBUSTNESS OF A FULLY CONNECTED RECURRENT NEURAL NETWORK. (Doctoral Dissertation). Clemson University. Retrieved from https://tigerprints.clemson.edu/all_dissertations/536
Chicago Manual of Style (16th Edition):
Wang, Xiaoyu. “ARCHITECTURE OPTIMIZATION, TRAINING CONVERGENCE AND NETWORK ESTIMATION ROBUSTNESS OF A FULLY CONNECTED RECURRENT NEURAL NETWORK.” 2010. Doctoral Dissertation, Clemson University. Accessed November 18, 2019.
https://tigerprints.clemson.edu/all_dissertations/536.
MLA Handbook (7th Edition):
Wang, Xiaoyu. “ARCHITECTURE OPTIMIZATION, TRAINING CONVERGENCE AND NETWORK ESTIMATION ROBUSTNESS OF A FULLY CONNECTED RECURRENT NEURAL NETWORK.” 2010. Web. 18 Nov 2019.
Vancouver:
Wang X. ARCHITECTURE OPTIMIZATION, TRAINING CONVERGENCE AND NETWORK ESTIMATION ROBUSTNESS OF A FULLY CONNECTED RECURRENT NEURAL NETWORK. [Internet] [Doctoral dissertation]. Clemson University; 2010. [cited 2019 Nov 18].
Available from: https://tigerprints.clemson.edu/all_dissertations/536.
Council of Science Editors:
Wang X. ARCHITECTURE OPTIMIZATION, TRAINING CONVERGENCE AND NETWORK ESTIMATION ROBUSTNESS OF A FULLY CONNECTED RECURRENT NEURAL NETWORK. [Doctoral Dissertation]. Clemson University; 2010. Available from: https://tigerprints.clemson.edu/all_dissertations/536
13.
Herzfeld, David James.
Modeling and Computational Framework for the Specification and Simulation of Large-scale Spiking Neural Networks.
Degree: 2011, Marquette University
URL: https://epublications.marquette.edu/theses_open/102
► Recurrently connected neural networks, in which synaptic connections between neurons can form directed cycles, have been used extensively in the literature to describe various neurophysiological…
(more)
▼ Recurrently connected
neural networks, in which synaptic connections between neurons can form directed cycles, have been used extensively in the literature to describe various neurophysiological phenomena, such as coordinate transformations during sensorimotor integration. Due to the directed cycles that can exist in
recurrent networks, there is no well-known way to a priori specify synaptic weights to elicit neuron spiking responses to stimuli based on available neurophysiology. Using a common mean field assumption, that synaptic inputs are uncorrelated for sufficiently large populations of neurons, we show that the connection topology and a neuron's response characteristics can be decoupled. This assumption allows specification of neuron steady-state responses independent of the connection topology.
Specification of neuron responses necessitates the creation of a novel simulator (computational framework) which allows modeling of large populations of connected spiking neurons. We describe the implementation of a spike-based computational framework, designed to take advantage of high performance computing architectures when available. We show that performance of the computational framework is improved using multiple message passing processes for large populations of neurons, resulting in a worst-case linear relationship between the number of neurons and the time required to complete a simulation.
Using the computational framework and the ability to specify neuron response characteristics independent of synaptic weights, we systematically investigate the effects of Hebbian learning on the hemodynamic response. Changes in the magnitude of the hemodynamic responses of
neural populations are assessed using a forward model that relates population synaptic currents to the blood oxygen dependant (BOLD) response via local field potentials. We show that the magnitude of the hemodynamic response is not a accurate indicator of underlying spiking activity for all
network topologies. Instead, we note that large changes in the aggregate response of the population (>50%) can results in a decrease in the overall magnitude of the BOLD signal. We hypothesize that the hemodynamic response magnitude changed due to fluctuations in the balance of excitatory and inhibitory inputs in
neural subpopulations. These results have important implications for mean-field models, suggesting that the underlying excitatory/inhibitory
neural dynamics within a population may need to be taken into account to accurately predict hemodynamic responses.
Advisors/Committee Members: Beardsley, Scott, Scheidt, Robert A., Struble, Craig A..
Subjects/Keywords: hemodynamic; neural network; recurrent; spiking; Biomedical Engineering and Bioengineering
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Herzfeld, D. J. (2011). Modeling and Computational Framework for the Specification and Simulation of Large-scale Spiking Neural Networks. (Thesis). Marquette University. Retrieved from https://epublications.marquette.edu/theses_open/102
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Herzfeld, David James. “Modeling and Computational Framework for the Specification and Simulation of Large-scale Spiking Neural Networks.” 2011. Thesis, Marquette University. Accessed November 18, 2019.
https://epublications.marquette.edu/theses_open/102.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Herzfeld, David James. “Modeling and Computational Framework for the Specification and Simulation of Large-scale Spiking Neural Networks.” 2011. Web. 18 Nov 2019.
Vancouver:
Herzfeld DJ. Modeling and Computational Framework for the Specification and Simulation of Large-scale Spiking Neural Networks. [Internet] [Thesis]. Marquette University; 2011. [cited 2019 Nov 18].
Available from: https://epublications.marquette.edu/theses_open/102.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Herzfeld DJ. Modeling and Computational Framework for the Specification and Simulation of Large-scale Spiking Neural Networks. [Thesis]. Marquette University; 2011. Available from: https://epublications.marquette.edu/theses_open/102
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
UCLA
14.
Li, Siyuan.
Application of Recurrent Neural Networks In Toxic Comment Classification.
Degree: Statistics, 2018, UCLA
URL: http://www.escholarship.org/uc/item/5f87h061
► Moderators of online discussion forums often struggle with controlling extremist comments on their platforms. To help provide an efficient and accurate tool to detect online…
(more)
▼ Moderators of online discussion forums often struggle with controlling extremist comments on their platforms. To help provide an efficient and accurate tool to detect online toxicity, we apply word2vec's Skip-Gram embedding vectors, Recurrent Neural Network models like Bidirectional Long Short-term Memory to tackle a toxic comment classification problem with a labeled dataset from Wikipedia Talk Page. We explore different pre-trained embedding vectors from larger corpora. We also assess the class imbalance issues associated with the dataset by employing sampling techniques and penalizing loss. Models we applied yield high overall accuracy with relatively low cost.
Subjects/Keywords: Statistics; classification; natural language processing; recurrent neural network; word2vec
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Li, S. (2018). Application of Recurrent Neural Networks In Toxic Comment Classification. (Thesis). UCLA. Retrieved from http://www.escholarship.org/uc/item/5f87h061
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Li, Siyuan. “Application of Recurrent Neural Networks In Toxic Comment Classification.” 2018. Thesis, UCLA. Accessed November 18, 2019.
http://www.escholarship.org/uc/item/5f87h061.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Li, Siyuan. “Application of Recurrent Neural Networks In Toxic Comment Classification.” 2018. Web. 18 Nov 2019.
Vancouver:
Li S. Application of Recurrent Neural Networks In Toxic Comment Classification. [Internet] [Thesis]. UCLA; 2018. [cited 2019 Nov 18].
Available from: http://www.escholarship.org/uc/item/5f87h061.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Li S. Application of Recurrent Neural Networks In Toxic Comment Classification. [Thesis]. UCLA; 2018. Available from: http://www.escholarship.org/uc/item/5f87h061
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
University of Ottawa
15.
Taylor, Adrian.
Anomaly-Based Detection of Malicious Activity in In-Vehicle Networks
.
Degree: 2017, University of Ottawa
URL: http://hdl.handle.net/10393/36120
► Modern automobiles have been proven vulnerable to hacking by security researchers. By exploiting vulnerabilities in the car's external interfaces, attackers can access a car's controller…
(more)
▼ Modern automobiles have been proven vulnerable to hacking by security researchers. By exploiting vulnerabilities in the car's external interfaces, attackers can access a car's controller area network (CAN) bus and cause malicious effects. We seek to detect these attacks on the bus as a last line of defence against automotive cyber attacks. The CAN bus standard defines a low-level message structure, upon which manufacturers layer their own proprietary command protocols; attacks must similarly be tailored for their target. This variability makes intrusion detection methods difficult to apply to the automotive CAN bus. Nevertheless, the bus traffic is generated by machines; thus we hypothesize that it can be characterized with machine learning, and that attacks produce anomalous traffic. Our goals are to show that anomaly detection trained without understanding of the message contents can detect attacks, and to create a framework for understanding how the characteristics of a novel attack can be used to predict its detectability.
We developed a model that describes attacks based on their effect on bus traffic, informed by a review of published material on car hacking in combination with analysis of CAN traffic from a 2012 Subaru Impreza. The model specifies three high-level categories of effects: attacks that insert foreign packets, attacks that affect packet timing, and attacks that only modify data within packets. Foreign packet attacks are trivially detectable. For timing-based anomalies, we developed features suitable for one-class classification methods. For packet stream data word anomalies, we adapted recurrent neural networks and multivariate Markov model methods to sequence anomaly detection and compared their performance.
We conducted experiments to evaluate our detection methods with special attention to the trade-off between precision and recall, given that a practical system requires a very low false alarm rate. The methods were evaluated by synthesizing anomalies within each attack category, parameterized to adjust their covertness. We generalize from the results to enable prediction of detection rates for new attacks using these methods.
Subjects/Keywords: anomaly detection;
cyber security;
intrusion detection;
recurrent neural network
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Taylor, A. (2017). Anomaly-Based Detection of Malicious Activity in In-Vehicle Networks
. (Thesis). University of Ottawa. Retrieved from http://hdl.handle.net/10393/36120
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Taylor, Adrian. “Anomaly-Based Detection of Malicious Activity in In-Vehicle Networks
.” 2017. Thesis, University of Ottawa. Accessed November 18, 2019.
http://hdl.handle.net/10393/36120.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Taylor, Adrian. “Anomaly-Based Detection of Malicious Activity in In-Vehicle Networks
.” 2017. Web. 18 Nov 2019.
Vancouver:
Taylor A. Anomaly-Based Detection of Malicious Activity in In-Vehicle Networks
. [Internet] [Thesis]. University of Ottawa; 2017. [cited 2019 Nov 18].
Available from: http://hdl.handle.net/10393/36120.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Taylor A. Anomaly-Based Detection of Malicious Activity in In-Vehicle Networks
. [Thesis]. University of Ottawa; 2017. Available from: http://hdl.handle.net/10393/36120
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
University of Waterloo
16.
Ruvinov, Igor.
Recurrent Neural Network Dual Resistance Control of Multiple Memory Shape Memory Alloys.
Degree: 2018, University of Waterloo
URL: http://hdl.handle.net/10012/13647
► Shape memory alloys (SMAs) are materials with extraordinary thermomechanical properties which have caused numerous engineering advances. NiTi SMAs in particular have been studied for decades…
(more)
▼ Shape memory alloys (SMAs) are materials with extraordinary thermomechanical properties which have caused numerous engineering advances. NiTi SMAs in particular have been studied for decades revealing many useful characteristics relative to other SMA compositions. Their application has correspondingly been widespread, seeing use in the robotics, automotive, and aerospace industries, among others. Nevertheless, several limitations inherent to SMAs exist which inhibit their applicability, including their inherent single transformation temperature and their complex hysteretic actuation behaviour.
To overcome the former challenge, one method utilizes high energy laser processing to perform localized vaporization of nickel and accurately adjust its transformation temperatures. This method can reliably produce NiTi SMAs with multiple monolithic transformation memories. There have also been attempts to overcome the latter of the aforementioned challenges by designing systems which model NiTi's hysteretic behaviour. When applied to actuators with a single transformation memory, these methods require the use of external sensors for modeling actuators with varying current and load, driving up the cost, weight, and complexity of the actuator. Embedding a second transformation memory with different phase into NiTi actuators can overcome this issue. By measuring electrical resistance across the two phases, sufficient information can be extracted for differentiating events caused by heating from those caused by applied load. The current study examines NiTi wires with two embedded transformation memories and utilizes recurrent neural networks for interpreting the sensed data. The knowledge gained through this study was used to create a recurrent neural network-based model which can accurately estimate the position and force applied to the NiTi actuator without the use of external sensors.
The first part of the research focused on obtaining a comprehensive thermomechanical characterization of laser processed and thermomechanically post-processed NiTi wires with two embedded transformation memories, with one memory exhibiting full SME and the second partial PE at room temperature. A second objective of this section was to acquire cycling data from the processed wires which would be used for training the artificial neural networks in the following section of the study. The selected laser processing and post-processing parameters resulted in a transformation temperature increase of 61.5°C and 35.3°C for Af and Ms, respectively, relative to base metal. Furthermore, the post-processing was found to successfully restore the majority of the lost mechanical properties, with the ultimate tensile strength recovered to 84% of its corresponding base metal value. This research resulted in the fabrication of NiTi wires with two distinct embedded transformation memories, exhibiting sufficient mechanical and cyclic properties for the next phase of the research.
Once an acceptable amount of NiTi actuation cycling data was acquired, the second…
Subjects/Keywords: Recurrent neural network; Shape memory alloys; Artificial intelligence
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Ruvinov, I. (2018). Recurrent Neural Network Dual Resistance Control of Multiple Memory Shape Memory Alloys. (Thesis). University of Waterloo. Retrieved from http://hdl.handle.net/10012/13647
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Ruvinov, Igor. “Recurrent Neural Network Dual Resistance Control of Multiple Memory Shape Memory Alloys.” 2018. Thesis, University of Waterloo. Accessed November 18, 2019.
http://hdl.handle.net/10012/13647.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Ruvinov, Igor. “Recurrent Neural Network Dual Resistance Control of Multiple Memory Shape Memory Alloys.” 2018. Web. 18 Nov 2019.
Vancouver:
Ruvinov I. Recurrent Neural Network Dual Resistance Control of Multiple Memory Shape Memory Alloys. [Internet] [Thesis]. University of Waterloo; 2018. [cited 2019 Nov 18].
Available from: http://hdl.handle.net/10012/13647.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Ruvinov I. Recurrent Neural Network Dual Resistance Control of Multiple Memory Shape Memory Alloys. [Thesis]. University of Waterloo; 2018. Available from: http://hdl.handle.net/10012/13647
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Victoria University of Wellington
17.
Chandra, Rohitash.
Problem Decomposition and
Adaptation in Cooperative
Neuro-Evolution.
Degree: 2012, Victoria University of Wellington
URL: http://hdl.handle.net/10063/2110
► One way to train neural networks is to use evolutionary algorithms such as cooperative coevolution - a method that decomposes the network's learnable parameters into…
(more)
▼ One way to train
neural networks is to use evolutionary algorithms
such as cooperative coevolution - a method that decomposes the
network's
learnable parameters into subsets, called subcomponents. Cooperative
coevolution gains advantage over other methods by evolving particular
subcomponents independently from the rest of the
network. Its success
depends strongly on how the problem decomposition is carried out.
This thesis suggests new forms of problem decomposition, based on a
novel and intuitive choice of modularity, and examines in detail at what
stage and to what extent the different decomposition methods should be
used. The new methods are evaluated by training feedforward networks
to solve pattern classification tasks, and by training
recurrent networks to
solve grammatical inference problems.
Efficient problem decomposition methods group interacting variables
into the same subcomponents. We examine the methods from the literature and provide an analysis of the nature of the
neural network optimization problem in terms of interacting variables. We then present a
novel problem decomposition method that groups interacting variables
and that can be generalized to
neural networks with more than a single
hidden layer.
We then incorporate local search into cooperative neuro-evolution. We
present a memetic cooperative coevolution method that takes into account
the cost of employing local search across several sub-populations.
The optimisation process changes during evolution in terms of diversity and interacting variables. To address this, we examine the adaptation
of the problem decomposition method during the evolutionary process. The results in this thesis show that the proposed methods improve performance
in terms of optimization time, scalability and robustness.
As a further test, we apply the problem decomposition and adaptive
cooperative coevolution methods for training
recurrent neural networks
on chaotic time series problems. The proposed methods show better performance
in terms of accuracy and robustness.
Advisors/Committee Members: Frean, Marcus, Zhang, Mengjie.
Subjects/Keywords: Neural networks; Cooperative coevolution; Recurrent network; Co-operative co-evolution
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Chandra, R. (2012). Problem Decomposition and
Adaptation in Cooperative
Neuro-Evolution. (Doctoral Dissertation). Victoria University of Wellington. Retrieved from http://hdl.handle.net/10063/2110
Chicago Manual of Style (16th Edition):
Chandra, Rohitash. “Problem Decomposition and
Adaptation in Cooperative
Neuro-Evolution.” 2012. Doctoral Dissertation, Victoria University of Wellington. Accessed November 18, 2019.
http://hdl.handle.net/10063/2110.
MLA Handbook (7th Edition):
Chandra, Rohitash. “Problem Decomposition and
Adaptation in Cooperative
Neuro-Evolution.” 2012. Web. 18 Nov 2019.
Vancouver:
Chandra R. Problem Decomposition and
Adaptation in Cooperative
Neuro-Evolution. [Internet] [Doctoral dissertation]. Victoria University of Wellington; 2012. [cited 2019 Nov 18].
Available from: http://hdl.handle.net/10063/2110.
Council of Science Editors:
Chandra R. Problem Decomposition and
Adaptation in Cooperative
Neuro-Evolution. [Doctoral Dissertation]. Victoria University of Wellington; 2012. Available from: http://hdl.handle.net/10063/2110
University of New Mexico
18.
Goudarzi, Alireza.
Theory and Practice of Computing with Excitable Dynamics.
Degree: Department of Computer Science, 2016, University of New Mexico
URL: https://digitalrepository.unm.edu/cs_etds/81
► Reservoir computing (RC) is a promising paradigm for time series processing. In this paradigm, the desired output is computed by combining measurements of an…
(more)
▼ Reservoir computing (RC) is a promising paradigm for time series processing. In this paradigm, the desired output is computed by combining measurements of an excitable system that responds to time-dependent exogenous stimuli. The excitable system is called a reservoir and measurements of its state are combined using a readout layer to produce a target output. The power of RC is attributed to an emergent short-term memory in dynamical systems and has been analyzed mathematically for both linear and nonlinear dynamical systems. The theory of RC treats only the macroscopic properties of the reservoir, without reference to the underlying medium it is made of. As a result, RC is particularly attractive for building computational devices using emerging technologies whose structure is not exactly controllable, such as self-assembled nanoscale circuits. RC has lacked a formal framework for performance analysis and prediction that goes beyond memory properties. To provide such a framework, here a mathematical theory of memory and information processing in ordered and disordered linear dynamical systems is developed. This theory analyzes the optimal readout layer for a given task. The focus of the theory is a standard model of RC, the echo state
network (ESN). An ESN consists of a fixed
recurrent neural network that is driven by an external signal. The dynamics of the
network is then combined linearly with readout weights to produce the desired output. The readout weights are calculated using linear regression.
Using an analysis of regression equations, the readout weights can be calculated using only the statistical properties of the reservoir dynamics, the input signal, and the desired output. The readout layer weights can be calculated from a priori knowledge of the desired function to be computed and the weight matrix of the reservoir. This formulation explicitly depends on the input weights, the reservoir weights, and the statistics of the target function. This formulation is used to bound the expected error of the system for a given target function. The effects of input-output correlation and complex
network structure in the reservoir on the computational performance of the system have been mathematically characterized. Far from the chaotic regime, ordered linear networks exhibit a homogeneous decay of memory in different dimensions, which keeps the input history coherent. As disorder is introduced in the structure of the
network, memory decay becomes inhomogeneous along different dimensions causing decoherence in the input history, and degradation in task-solving performance. Close to the chaotic regime, the ordered systems show loss of temporal information in the input history, and therefore inability to solve tasks. However, by introducing disorder and therefore heterogeneous decay of memory the temporal information of input history is preserved and the task-solving performance is recovered. Thus for systems at the edge of chaos, disordered structure may enhance temporal information processing. Although the…
Advisors/Committee Members: Darko Stefanovic, Christof Teuscher, Lance Williams, Melanie Moses.
Subjects/Keywords: reservoir computing; recurrent neural network; excitable dynamics; dynamical systems; Computer Sciences
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Goudarzi, A. (2016). Theory and Practice of Computing with Excitable Dynamics. (Doctoral Dissertation). University of New Mexico. Retrieved from https://digitalrepository.unm.edu/cs_etds/81
Chicago Manual of Style (16th Edition):
Goudarzi, Alireza. “Theory and Practice of Computing with Excitable Dynamics.” 2016. Doctoral Dissertation, University of New Mexico. Accessed November 18, 2019.
https://digitalrepository.unm.edu/cs_etds/81.
MLA Handbook (7th Edition):
Goudarzi, Alireza. “Theory and Practice of Computing with Excitable Dynamics.” 2016. Web. 18 Nov 2019.
Vancouver:
Goudarzi A. Theory and Practice of Computing with Excitable Dynamics. [Internet] [Doctoral dissertation]. University of New Mexico; 2016. [cited 2019 Nov 18].
Available from: https://digitalrepository.unm.edu/cs_etds/81.
Council of Science Editors:
Goudarzi A. Theory and Practice of Computing with Excitable Dynamics. [Doctoral Dissertation]. University of New Mexico; 2016. Available from: https://digitalrepository.unm.edu/cs_etds/81
19.
Oskarsson, Gustav.
Aktieprediktion med neurala nätverk : En jämförelse av statistiska modeller, neurala nätverk och kombinerade neurala nätverk.
Degree: 2019, , Department of Industrial Economics
URL: http://urn.kb.se/resolve?urn=urn:nbn:se:bth-18214
► This study is about prediction of the stockmarket through a comparison of neural networks and statistical models. The study aims to improve the accuracy…
(more)
▼ This study is about prediction of the stockmarket through a comparison of neural networks and statistical models. The study aims to improve the accuracy of stock prediction. Much of the research made on predicting shares deals with statistical models, but also neural networks and then mainly the types RNN and CNN. No research has been done on how these neural networks can be combined, which is why this study aims for this. Tests are made on statistical models, neural networks and combined neural networks to predict stocks at minute level. The result shows that a combination of two neural networks of type RNN gives the best accuracy in the prediction of shares. The accuracy of the predictions increases further if these combined neural networks are trained to predict different time horizons. In addition to tests for accuracy, simulations have also been made which also confirm that there is some possibility to predict shares. Two combined RNNs gave best results, but in the simulations, even CNN made good predictions. One conclusion can be drawn that the stock market is not entirely effective as some opportunity to predict future values exists. Another conclusion is that neural networks are better than statistical models to predict stocks if the neural networks are combined and are of type RNN.
Denna studie behandlar prediktion av aktier genom en jämförelse av neurala nätverk och statistiska modeller. Studien syftar till att förbättra noggrannheten för aktieprediktion. Mycket av den forskning som gjorts om att förutspå aktier behandlar statistiska modeller, men även neurala nätverk och då främst typerna RNN och CNN. Ingen forskning har dock gjorts på hur dessa neurala nätverk kan kombineras, varför denna studie syftar till just detta. Tester är gjorda på statistiska modeller, neurala nätverk och kombinerade neurala nätverk för att förutspå aktier på minutnivå. Resultatet visar att en kombination av två neurala nätverk av typen RNN ger bäst noggrannhet vid prediktion av aktier. Noggrannheten i prediktionerna ökar ytterligare om dessa neurala nätverk tränas för att förutspå olika tidshorisont. Utöver tester för prediktionernas noggrannhet har även simuleringar genomförts som även de bekräftar att viss möjlighet finns att förutspå aktier. Två kombinerade RNN gav bra resultat, men här visade även CNN bra prediktioner. En slutsats kan dras om att aktiemarknaden inte är helt effektiv då viss möjlighet att förutspå framtida värden finns. Ytterligare en slutsats är att neurala nätverk är bättre än statistiska modeller till att förutspå aktier om de neurala nätverken kombineras och är av typen RNN.
Subjects/Keywords: neural network; stock market; recurrent neural network; neuralt nätverk; aktiemarknad; recurrent neural network; Other Engineering and Technologies not elsewhere specified; Övrig annan teknik
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Oskarsson, G. (2019). Aktieprediktion med neurala nätverk : En jämförelse av statistiska modeller, neurala nätverk och kombinerade neurala nätverk. (Thesis). , Department of Industrial Economics. Retrieved from http://urn.kb.se/resolve?urn=urn:nbn:se:bth-18214
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Oskarsson, Gustav. “Aktieprediktion med neurala nätverk : En jämförelse av statistiska modeller, neurala nätverk och kombinerade neurala nätverk.” 2019. Thesis, , Department of Industrial Economics. Accessed November 18, 2019.
http://urn.kb.se/resolve?urn=urn:nbn:se:bth-18214.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Oskarsson, Gustav. “Aktieprediktion med neurala nätverk : En jämförelse av statistiska modeller, neurala nätverk och kombinerade neurala nätverk.” 2019. Web. 18 Nov 2019.
Vancouver:
Oskarsson G. Aktieprediktion med neurala nätverk : En jämförelse av statistiska modeller, neurala nätverk och kombinerade neurala nätverk. [Internet] [Thesis]. , Department of Industrial Economics; 2019. [cited 2019 Nov 18].
Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:bth-18214.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Oskarsson G. Aktieprediktion med neurala nätverk : En jämförelse av statistiska modeller, neurala nätverk och kombinerade neurala nätverk. [Thesis]. , Department of Industrial Economics; 2019. Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:bth-18214
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Oklahoma State University
20.
Phan, Manh Cong.
Recurrent Neural Networks: Error Surface Analysis and Improved Training.
Degree: Electrical Engineering, 2014, Oklahoma State University
URL: http://hdl.handle.net/11244/15063
► Recurrent neural networks (RNNs) have powerful computational abilities and could be used in a variety of applications; however, training these networks is still a difficult…
(more)
▼ Recurrent neural networks (RNNs) have powerful computational abilities and could be used in a variety of applications; however, training these networks is still a difficult problem. One of the reasons that makes RNN training, especially using batch, gradient-based methods, difficult is the existence of spurious valleys in the error surface. In this work, a mathematical framework was developed to analyze the spurious valleys that appear in most practical RNN architectures, no matter their size. The insights gained from this analysis suggested a new procedure for improving the training process. The procedure uses a batch training method based on a modified version of the Levenberg-Marquardt algorithm. This new procedure mitigates the effects of spurious valleys in the error surface of RNNs. The results on a variety of test problems show that the new procedure is consistently better than existing training algorithms (both batch and stochastic) for training RNNs. Also, a framework for
neural network controllers based on the model reference adaptive control (MRAC) architecture was developed. This architecture has been used before, but the difficulties in training RNNs have limited its use. The new training procedures have made MRAC more attractive. The updated MRAC framework is very flexible, and incorporates disturbance rejection, regulation and tracking. The simulation and testing results on several real systems show that this type of
neural control is well-suited for highly nonlinear plants.
Advisors/Committee Members: Hagan, Martin T. (advisor), Latino, Carl (committee member), Hutchens, Chris (committee member), Kable, Anthony (committee member).
Subjects/Keywords: error surface; neural control; recurrent neural network; spurious valley; system identification; training
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Phan, M. C. (2014). Recurrent Neural Networks: Error Surface Analysis and Improved Training. (Thesis). Oklahoma State University. Retrieved from http://hdl.handle.net/11244/15063
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Phan, Manh Cong. “Recurrent Neural Networks: Error Surface Analysis and Improved Training.” 2014. Thesis, Oklahoma State University. Accessed November 18, 2019.
http://hdl.handle.net/11244/15063.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Phan, Manh Cong. “Recurrent Neural Networks: Error Surface Analysis and Improved Training.” 2014. Web. 18 Nov 2019.
Vancouver:
Phan MC. Recurrent Neural Networks: Error Surface Analysis and Improved Training. [Internet] [Thesis]. Oklahoma State University; 2014. [cited 2019 Nov 18].
Available from: http://hdl.handle.net/11244/15063.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Phan MC. Recurrent Neural Networks: Error Surface Analysis and Improved Training. [Thesis]. Oklahoma State University; 2014. Available from: http://hdl.handle.net/11244/15063
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Louisiana State University
21.
Firth, Robert James.
A Novel Recurrent Convolutional Neural Network for Ocean and Weather Forecasting.
Degree: PhD, Computer Sciences, 2016, Louisiana State University
URL: etd-04112016-151259
;
https://digitalcommons.lsu.edu/gradschool_dissertations/2099
► Numerical weather prediction is a computationally expensive task that requires not only the numerical solution to a complex set of non-linear partial differential equations, but…
(more)
▼ Numerical weather prediction is a computationally expensive task that requires not only the numerical solution to a complex set of non-linear partial differential equations, but also the creation of a parameterization scheme to estimate sub-grid scale phenomenon. The proposed method is an alternative approach to developing a mesoscale meteorological model – a modified recurrent convolutional neural network that learns to simulate the solution to these equations. Along with an appropriate time integration scheme and learning algorithm, this method can be used to create multi-day forecasts for a large region. The learning method presented is an extended form of Backpropagation Through Time for a recurrent network with outputs that feed back through as inputs only after undergoing a fixed transformation. An initial implementation of this approach has been created that forecasts for 2,744 locations across the southeastern United States at 36 vertical levels of the atmosphere, and 119,000 locations across the Atlantic Ocean at 39 vertical levels. These models, called LM3 and LOM, forecast wind speed, temperature, geopotential height, and rainfall for weather forecasting and water current speed, temperature, and salinity for ocean forecasting. Experimental results show that the new approach is 3.6 times more efficient at forecasting the ocean and 16 times more efficient at forecasting the atmosphere. The new approach showed forecast skill by beating the accuracy of two models, persistence and climatology, and was more accurate than the Navy NCOM model on 16 of the first 17 layers of the ocean below the surface (2 meters to 70 meters) for forecasting salinity and 15 of the first 17 layers for forecasting temperature. The new approach was also more accurate than the RAP model at forecasting wind speed on 7 layers, specific humidity on 7 layers, relative humidity on 6 layers, and temperature on 3 layers, with competitive results elsewhere.
Subjects/Keywords: time series; spatial; temporal; time step network; convolutional; recurrent; neural network; weather forecasting; ocean forecasting
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Firth, R. J. (2016). A Novel Recurrent Convolutional Neural Network for Ocean and Weather Forecasting. (Doctoral Dissertation). Louisiana State University. Retrieved from etd-04112016-151259 ; https://digitalcommons.lsu.edu/gradschool_dissertations/2099
Chicago Manual of Style (16th Edition):
Firth, Robert James. “A Novel Recurrent Convolutional Neural Network for Ocean and Weather Forecasting.” 2016. Doctoral Dissertation, Louisiana State University. Accessed November 18, 2019.
etd-04112016-151259 ; https://digitalcommons.lsu.edu/gradschool_dissertations/2099.
MLA Handbook (7th Edition):
Firth, Robert James. “A Novel Recurrent Convolutional Neural Network for Ocean and Weather Forecasting.” 2016. Web. 18 Nov 2019.
Vancouver:
Firth RJ. A Novel Recurrent Convolutional Neural Network for Ocean and Weather Forecasting. [Internet] [Doctoral dissertation]. Louisiana State University; 2016. [cited 2019 Nov 18].
Available from: etd-04112016-151259 ; https://digitalcommons.lsu.edu/gradschool_dissertations/2099.
Council of Science Editors:
Firth RJ. A Novel Recurrent Convolutional Neural Network for Ocean and Weather Forecasting. [Doctoral Dissertation]. Louisiana State University; 2016. Available from: etd-04112016-151259 ; https://digitalcommons.lsu.edu/gradschool_dissertations/2099
Georgia Tech
22.
Chen, Shiyang.
Spatiotemporal modeling of brain dynamics using machine learning approaches.
Degree: PhD, Biomedical Engineering (Joint GT/Emory Department), 2017, Georgia Tech
URL: http://hdl.handle.net/1853/60677
► Resting state fMRI (rfMRI) has been widely used to study functional connectivity of human brains. Although most of the analysis methods to date have assumed…
(more)
▼ Resting state fMRI (rfMRI) has been widely used to study functional connectivity of human brains. Although most of the analysis methods to date have assumed the resting state to be stationary, this assumption is invalid when significant changes in functional connectivity occur within a short period of time, as indicated by recent literature. Hence, resting state analysis can be improved by accounting for temporal changes. Recent literature has reached a consensus that the brain is frequently switching among a number of quasi-stable states. To capture these temporal dynamics and derive both spatial and temporal characteristics of the states simultaneously, we propose two machine learning models that incorporate spatial and temporal information. First, Gaussian hidden Markov model (GHMM) has been applied to systematically model the brain state switching processing in rfMRI. We have shown its stability and reproducibility on healthy controls and then demonstrate its application in deriving biomarkers of prenatal alcohol exposure. Second, we have introduced
recurrent neural network to investigating individual uniqueness using fMRI and visualized the features that can distinguish individuals, which is considered as a fingerprint of the brain’s function.
Advisors/Committee Members: Hu, Xiaoping (advisor), Keilholz, Shella (advisor), Lee, Chin-Hui (committee member), Sathian, Krish (committee member), Ting, Lena (committee member), Qiu, Deqiang (committee member).
Subjects/Keywords: Functional magnetic resonance imaging; Resting-state; Dynamic model; Individual identification; Gated recurrent unit; Recurrent neural network
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Chen, S. (2017). Spatiotemporal modeling of brain dynamics using machine learning approaches. (Doctoral Dissertation). Georgia Tech. Retrieved from http://hdl.handle.net/1853/60677
Chicago Manual of Style (16th Edition):
Chen, Shiyang. “Spatiotemporal modeling of brain dynamics using machine learning approaches.” 2017. Doctoral Dissertation, Georgia Tech. Accessed November 18, 2019.
http://hdl.handle.net/1853/60677.
MLA Handbook (7th Edition):
Chen, Shiyang. “Spatiotemporal modeling of brain dynamics using machine learning approaches.” 2017. Web. 18 Nov 2019.
Vancouver:
Chen S. Spatiotemporal modeling of brain dynamics using machine learning approaches. [Internet] [Doctoral dissertation]. Georgia Tech; 2017. [cited 2019 Nov 18].
Available from: http://hdl.handle.net/1853/60677.
Council of Science Editors:
Chen S. Spatiotemporal modeling of brain dynamics using machine learning approaches. [Doctoral Dissertation]. Georgia Tech; 2017. Available from: http://hdl.handle.net/1853/60677
Virginia Tech
23.
Wang, Wei.
Event Detection and Extraction from News Articles.
Degree: PhD, Computer Science, 2018, Virginia Tech
URL: http://hdl.handle.net/10919/82238
► Event extraction is a type of information extraction(IE) that works on extracting the specific knowledge of certain incidents from texts. Nowadays the amount of available…
(more)
▼ Event extraction is a type of information extraction(IE) that works on extracting the specific knowledge of certain incidents from texts. Nowadays the amount of available information (such as news, blogs, and social media) grows in exponential order. Therefore, it becomes imperative to develop algorithms that automatically extract the machine-readable information from large volumes of text data. In this dissertation, we focus on three problems in obtaining event-related information from news articles. (1) The first effort is to comprehensively analyze the performance and challenges in current large-scale event encoding systems. (2) The second problem involves event detection and critical information extractions from news articles. (3) Third, the efforts concentrate on event-encoding which aims to extract event extent and arguments from texts.
We start by investigating the two large-scale event extraction systems (ICEWS and GDELT) in the political science domain. We design a set of experiments to evaluate the quality of the extracted events from the two target systems, in terms of reliability and correctness. The results show that there exist significant discrepancies between the outputs of automated systems and hand-coded system and the accuracy of both systems are far away from satisfying. These findings provide preliminary background and set the foundation for using advanced machine learning algorithms for event related information extraction.
Inspired by the successful application of deep learning in Natural Language Processing (NLP), we propose a Multi-Instance Convolutional
Neural Network (MI-CNN) model for event detection and critical sentences extraction without sentence level labels. To evaluate the model, we run a set of experiments on a real-world protest event dataset. The result shows that our model could be able to outperform the strong baseline models and extract the meaningful key sentences without domain knowledge and manually designed features.
We also extend the MI-CNN model and propose an MIMTRNN model for event extraction with distant supervision to overcome the problem of lacking fine level labels and small size training data. The proposed MIMTRNN model systematically integrates the RNN, Multi-Instance Learning, and Multi-Task Learning into a unified framework. The RNN module aims to encode into the representation of entity mentions the sequential information as well as the dependencies between event arguments, which are very useful in the event extraction task. The Multi-Instance Learning paradigm makes the system does not require the precise labels in entity mention level and make it perfect to work together with distant supervision for event extraction. And the Multi-Task Learning module in our approach is designed to alleviate the potential overfitting problem caused by the relatively small size of training data. The results of the experiments on two real-world datasets(Cyber-Attack and Civil Unrest) show that our model could be able to benefit from the advantage of each component and…
Advisors/Committee Members: Ramakrishnan, Narendran (committeechair), North, Christopher L. (committee member), Tandon, Ravi (committee member), Lu, Chang Tien (committee member), Rangwala, Huzefa (committee member).
Subjects/Keywords: Event Detection; Event Encoding; Deep Learning; Convolutional Neural Network; Recurrent Neural Network; Multi Instance Learning; Multi Task Learning
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Wang, W. (2018). Event Detection and Extraction from News Articles. (Doctoral Dissertation). Virginia Tech. Retrieved from http://hdl.handle.net/10919/82238
Chicago Manual of Style (16th Edition):
Wang, Wei. “Event Detection and Extraction from News Articles.” 2018. Doctoral Dissertation, Virginia Tech. Accessed November 18, 2019.
http://hdl.handle.net/10919/82238.
MLA Handbook (7th Edition):
Wang, Wei. “Event Detection and Extraction from News Articles.” 2018. Web. 18 Nov 2019.
Vancouver:
Wang W. Event Detection and Extraction from News Articles. [Internet] [Doctoral dissertation]. Virginia Tech; 2018. [cited 2019 Nov 18].
Available from: http://hdl.handle.net/10919/82238.
Council of Science Editors:
Wang W. Event Detection and Extraction from News Articles. [Doctoral Dissertation]. Virginia Tech; 2018. Available from: http://hdl.handle.net/10919/82238
24.
Hijazi, Issa.
Animal ID Tag Recognition with Convolutional and Recurrent Neural Network : Identifying digits from a number sequence with RCNN.
Degree: Informatics, 2019, University of Skövde
URL: http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-17031
► Major advances in machine learning have made image recognition applications, with Artificial Neural Network, blossom over the recent years. The aim of this thesis…
(more)
▼ Major advances in machine learning have made image recognition applications, with Artificial Neural Network, blossom over the recent years. The aim of this thesis was to find a solution to recognize digits from a number sequence on an ID tag, used to identify farm animals, with the help of image recognition. A Recurrent Convolutional Neural Network solution called PPNet was proposed and tested on a data set called Animal Identification Tags. A transfer learning method was also used to test if it could help PPNet generalize and better recognize digits. PPNet was then compared against Microsoft Azures own image recognition API, to determine how PPNet compares to a general solution. PPNet, while not performing as good, still managed to achieve competitive results to the Azure API.
Subjects/Keywords: Machine Learning; Convolutional Neural Network; Recurrent Neural Network; Transfer learning; Microsoft Azure; Computer Sciences; Datavetenskap (datalogi)
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Hijazi, I. (2019). Animal ID Tag Recognition with Convolutional and Recurrent Neural Network : Identifying digits from a number sequence with RCNN. (Thesis). University of Skövde. Retrieved from http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-17031
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Hijazi, Issa. “Animal ID Tag Recognition with Convolutional and Recurrent Neural Network : Identifying digits from a number sequence with RCNN.” 2019. Thesis, University of Skövde. Accessed November 18, 2019.
http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-17031.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Hijazi, Issa. “Animal ID Tag Recognition with Convolutional and Recurrent Neural Network : Identifying digits from a number sequence with RCNN.” 2019. Web. 18 Nov 2019.
Vancouver:
Hijazi I. Animal ID Tag Recognition with Convolutional and Recurrent Neural Network : Identifying digits from a number sequence with RCNN. [Internet] [Thesis]. University of Skövde; 2019. [cited 2019 Nov 18].
Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-17031.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Hijazi I. Animal ID Tag Recognition with Convolutional and Recurrent Neural Network : Identifying digits from a number sequence with RCNN. [Thesis]. University of Skövde; 2019. Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-17031
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Brno University of Technology
25.
Huf, Petr.
Machine Learning Strategies in Electronic Trading
.
Degree: 2014, Brno University of Technology
URL: http://hdl.handle.net/11012/56492
► Úspěšné obchodování na trzích je snem mnoha lidí. Zajímavým odvětvím tohoto byznysu je elektronické obchodování, kde obchodní strategie běží na počítači bez jakéhokoliv zásahu člověka.…
(more)
▼ Úspěšné obchodování na trzích je snem mnoha lidí. Zajímavým odvětvím tohoto byznysu je elektronické obchodování, kde obchodní strategie běží na počítači bez jakéhokoliv zásahu člověka. Tento způsob obchodování poskytuje spoustu volného času a vysoké příjmy. Tato práce je zaměřena na využití neuronových sítí při stavbě takovéto obchodní strategie. Jako základ byla použita již existující rekurentní neuronová síť, která byla postupně modifikována podle potřeb pro obchodování. Výsledkem je neuronová síť předpovídající budoucí pohyby trhu. Obchodní strategie používající tuto neuronovou síť dokáže na burze úspěšně obchodovat.; Successful stock trading is a dream of many people. Eletronic trading is an interesting branch of this business. The trading strategy runs on the computer all the time without any human intervention. This way of trading provides a lot of free time and high earnings. This thesis is aimed at usage of
neural networks in building this type of trading strategy. An already existing
recurrent neural network was used as a basis and was modified for the needs of trading. The result is a
neural network which predicts future market moves. The trading strategy based on this
neural network is able to perform a successful trading.
Advisors/Committee Members: Černocký, Jan (advisor).
Subjects/Keywords: neuronová síť;
rekurentní neuronová síť;
burza;
obchodování;
trh;
profit;
model;
neural network;
recurrent neural network;
stock exchange;
trading;
market;
profit;
model
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Huf, P. (2014). Machine Learning Strategies in Electronic Trading
. (Thesis). Brno University of Technology. Retrieved from http://hdl.handle.net/11012/56492
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Huf, Petr. “Machine Learning Strategies in Electronic Trading
.” 2014. Thesis, Brno University of Technology. Accessed November 18, 2019.
http://hdl.handle.net/11012/56492.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Huf, Petr. “Machine Learning Strategies in Electronic Trading
.” 2014. Web. 18 Nov 2019.
Vancouver:
Huf P. Machine Learning Strategies in Electronic Trading
. [Internet] [Thesis]. Brno University of Technology; 2014. [cited 2019 Nov 18].
Available from: http://hdl.handle.net/11012/56492.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Huf P. Machine Learning Strategies in Electronic Trading
. [Thesis]. Brno University of Technology; 2014. Available from: http://hdl.handle.net/11012/56492
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
University of Western Ontario
26.
Wang, Xindi.
Incorporating Figure Captions and Descriptive Text into Mesh Term Indexing: A Deep Learning Approach.
Degree: 2019, University of Western Ontario
URL: https://ir.lib.uwo.ca/etd/6263
► The exponential increase of available documents online makes document classification an important application in natural language processing. The goal of text classification is to automatically…
(more)
▼ The exponential increase of available documents online makes document classification an important application in natural language processing. The goal of text classification is to automatically assign categories to documents. Traditional text classifiers depend on features, such as, vocabulary and user-specified information which mainly relies on prior knowledge. In contrast, deep learning automatically learns effective features from data instead of adopting human-designed features. In this thesis, we specifically focus on biomedical document classification. Beyond text information from abstract and title, we also consider image and table captions, as well as paragraphs associated with images and tables, which we demonstrate to be an important feature source to our method.
Subjects/Keywords: text classification; MeSH term indexing; deep learning; convolutional neural network; recurrent neural network; attention model; Artificial Intelligence and Robotics
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Wang, X. (2019). Incorporating Figure Captions and Descriptive Text into Mesh Term Indexing: A Deep Learning Approach. (Thesis). University of Western Ontario. Retrieved from https://ir.lib.uwo.ca/etd/6263
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Wang, Xindi. “Incorporating Figure Captions and Descriptive Text into Mesh Term Indexing: A Deep Learning Approach.” 2019. Thesis, University of Western Ontario. Accessed November 18, 2019.
https://ir.lib.uwo.ca/etd/6263.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Wang, Xindi. “Incorporating Figure Captions and Descriptive Text into Mesh Term Indexing: A Deep Learning Approach.” 2019. Web. 18 Nov 2019.
Vancouver:
Wang X. Incorporating Figure Captions and Descriptive Text into Mesh Term Indexing: A Deep Learning Approach. [Internet] [Thesis]. University of Western Ontario; 2019. [cited 2019 Nov 18].
Available from: https://ir.lib.uwo.ca/etd/6263.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Wang X. Incorporating Figure Captions and Descriptive Text into Mesh Term Indexing: A Deep Learning Approach. [Thesis]. University of Western Ontario; 2019. Available from: https://ir.lib.uwo.ca/etd/6263
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
27.
Hannum, Andrew.
RNN-Based Generation of Polyphonic Music and Jazz Improvisation.
Degree: MS, Computer Science, 2018, U of Denver
URL: https://digitalcommons.du.edu/etd/1532
► This paper presents techniques developed for algorithmic composition of both polyphonic music, and of simulated jazz improvisation, using multiple novel data sources and the…
(more)
▼ This paper presents techniques developed for algorithmic composition of both polyphonic music, and of simulated jazz improvisation, using multiple novel data sources and the character-based
recurrent neural network architecture
char-rnn. In addition, techniques and tooling are presented aimed at using the results of the algorithmic composition to create exercises for musical pedagogy.
Advisors/Committee Members: Mario A. Lopez, Ph.D..
Subjects/Keywords: Artificial intelligence; Generative music; Jazz improvisation; Machine learning; Neural network; Recurrent neural network; Artificial Intelligence and Robotics; Computer Sciences; Music Pedagogy
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Hannum, A. (2018). RNN-Based Generation of Polyphonic Music and Jazz Improvisation. (Thesis). U of Denver. Retrieved from https://digitalcommons.du.edu/etd/1532
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Hannum, Andrew. “RNN-Based Generation of Polyphonic Music and Jazz Improvisation.” 2018. Thesis, U of Denver. Accessed November 18, 2019.
https://digitalcommons.du.edu/etd/1532.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Hannum, Andrew. “RNN-Based Generation of Polyphonic Music and Jazz Improvisation.” 2018. Web. 18 Nov 2019.
Vancouver:
Hannum A. RNN-Based Generation of Polyphonic Music and Jazz Improvisation. [Internet] [Thesis]. U of Denver; 2018. [cited 2019 Nov 18].
Available from: https://digitalcommons.du.edu/etd/1532.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Hannum A. RNN-Based Generation of Polyphonic Music and Jazz Improvisation. [Thesis]. U of Denver; 2018. Available from: https://digitalcommons.du.edu/etd/1532
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Brno University of Technology
28.
Zvěřina, Lukáš.
Predikce datového toku v počítačových sítích
.
Degree: 2013, Brno University of Technology
URL: http://hdl.handle.net/11012/26771
► Předmětem této diplomové práce bylo seznámit se s problematikou predikce výskytu dat v počítačových sítích. Dále se tato práce zabývala síťovým provozem a analýzou jeho…
(more)
▼ Předmětem této diplomové práce bylo seznámit se s problematikou predikce výskytu dat v počítačových sítích. Dále se tato práce zabývala síťovým provozem a analýzou jeho vlastností. V této práci byly rozebrány možnosti predikce síťového provozu pomocí FARIMA modelu, teorii chaosu s Lyapunovým exponentem a pomocí neuronových sítí. Nejpodrobněji zde byly probrány možnosti predikce, se zaměřením na neuronové sítě. Konkrétně tedy hlavně na rekurentní neuronové sítě. Predikce se prováděly pomocí programu Matlab ve vývojovém prostředí
Neural Network Toolbox, kde byly vytvořeny, natrénovány a otestovány neuronové sítě pro predikci konkrétních druhů síťového provozu. Pro testování byly vybrány Elmanova síť, NARX síť a obecná LRN rekurentní síť. Získané výsledky byly přehledně zpracovány do tabulek a vyneseny do grafických závislostí před a po použití navržené predikční techniky se závěrečným zhodnocením.; The aim of this thesis was to study problems of prediction of data in computer networks. Furthermore, this work deals with
network traffic and analyzing its properties. In this study were analyzed the possibilities of
network traffic prediction using Farima model, the theory of chaos with Lyapunov exponents and
neural networks. Possibilities of prediction with the focus on
neural network were discussed in detail here, mainly on
recurrent neural networks. Prediction was performed in Matlab development environment in
Neural Network Toolbox, where they were created, trained and evaluated
neural network to predict specific types of
network traffic. For testing were selected Elman
network NARX
network and general LRN
recurrent network. The results were clearly organized into tables and plotted in graphical relationships before and after the use of predictive techniques designed to final evaluation.
Advisors/Committee Members: Vychodil, Petr (advisor).
Subjects/Keywords: Síťový provoz;
dynamická alokace šířky pásma;
predikce;
rekurentní neuronová síť;
Neural Network Toolbox;
Network traffic;
dynamic bandwidth allocation;
prediction;
recurrent neural network;
Neural Network Toolbox
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Zvěřina, L. (2013). Predikce datového toku v počítačových sítích
. (Thesis). Brno University of Technology. Retrieved from http://hdl.handle.net/11012/26771
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Zvěřina, Lukáš. “Predikce datového toku v počítačových sítích
.” 2013. Thesis, Brno University of Technology. Accessed November 18, 2019.
http://hdl.handle.net/11012/26771.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Zvěřina, Lukáš. “Predikce datového toku v počítačových sítích
.” 2013. Web. 18 Nov 2019.
Vancouver:
Zvěřina L. Predikce datového toku v počítačových sítích
. [Internet] [Thesis]. Brno University of Technology; 2013. [cited 2019 Nov 18].
Available from: http://hdl.handle.net/11012/26771.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Zvěřina L. Predikce datového toku v počítačových sítích
. [Thesis]. Brno University of Technology; 2013. Available from: http://hdl.handle.net/11012/26771
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Brno University of Technology
29.
Člupek, Vlastimil.
Nelineární analýza a predikce síťového provozu
.
Degree: 2012, Brno University of Technology
URL: http://hdl.handle.net/11012/8976
► Tato diplomová práce se zabývá síťovým provozem a analýzou jeho vlastností. V této práci jsou rozebrány možnosti predikce síťového provozu pomocí FARIMA modelu, teorii chaosu…
(more)
▼ Tato diplomová práce se zabývá síťovým provozem a analýzou jeho vlastností. V této práci jsou rozebrány možnosti predikce síťového provozu pomocí FARIMA modelu, teorii chaosu s Lyapunovým exponentem a pomocí neuronových sítí. Největší pozornost byla věnována predikci síťového provozu pomocí neuronových sítí. V prostředí Matlab s využitím
Neural Network Toolbox byly vytvořeny, natrénovány a otestovány rekurentní sítě pro predikci konkrétních druhů síťového provozu, který byl odchycen na lokální síti. K testování predikce síťového provozu byla vybrána Elmanova síť, LRN a NARX síť, dosažené výsledky byly diskutovány. Dále je v práci uvedena oblast využití schopnosti predikce síťového provozu, je zde uveden návrh systému pro dynamickou alokaci šířky pásma s konkrétním popisem jeho predikční části. V práci je také uvedeno možné využití navrhnutého systému pro dynamickou alokaci šířky pásma.; This thesis deal with an analysis of
network traffic and its properties. In this thesis are discussed possibilities of prediction
network traffic by FARIMA model, theory of chaos with Lyapunov exponent and by
neural networks. The biggest attention was dedicated to prediction
network traffic by
neural networks. In Matlab with using
Neural Network Toolbox were created, trained and tested
recurrent networks for prediction specific types of
network traffics, which was captured on local
network. There were choosed Elman
network, LRN and NARX
network to test the prediction of
network traffic, results were discussed. Thesis also introduce area of application ability prediction of
network traffic, there is introduce design of system for dynamic allocation bandwidth with particular description of its prediction part. Thesis also states possible use designed system for dynamic allocation of bandwidth.
Advisors/Committee Members: Vychodil, Petr (advisor).
Subjects/Keywords: Síťový provoz;
predikce;
rekurentní neuronová síť;
Neural Network Toolbox;
dynamická alokace šířky pásma.;
Network traffic;
prediction;
recurrent neural network;
Neural Network Toolbox;
dynamic bandwidth allocation.
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Člupek, V. (2012). Nelineární analýza a predikce síťového provozu
. (Thesis). Brno University of Technology. Retrieved from http://hdl.handle.net/11012/8976
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Člupek, Vlastimil. “Nelineární analýza a predikce síťového provozu
.” 2012. Thesis, Brno University of Technology. Accessed November 18, 2019.
http://hdl.handle.net/11012/8976.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Člupek, Vlastimil. “Nelineární analýza a predikce síťového provozu
.” 2012. Web. 18 Nov 2019.
Vancouver:
Člupek V. Nelineární analýza a predikce síťového provozu
. [Internet] [Thesis]. Brno University of Technology; 2012. [cited 2019 Nov 18].
Available from: http://hdl.handle.net/11012/8976.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Člupek V. Nelineární analýza a predikce síťového provozu
. [Thesis]. Brno University of Technology; 2012. Available from: http://hdl.handle.net/11012/8976
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
30.
Ahrneteg, Jakob.
Semantic Segmentation of Historical Document Images Using Recurrent Neural Networks.
Degree: 2019, , Department of Software Engineering
URL: http://urn.kb.se/resolve?urn=urn:nbn:se:bth-18219
► Background. This thesis focuses on the task of historical document semantic segmentation with recurrent neural networks. Document semantic segmentation involves the segmentation of a…
(more)
▼ Background. This thesis focuses on the task of historical document semantic segmentation with recurrent neural networks. Document semantic segmentation involves the segmentation of a page into different meaningful regions and is an important prerequisite step of automated document analysis and digitisation with optical character recognition. At the time of writing, convolutional neural network based solutions are the state-of-the-art for analyzing document images while the use of recurrent neural networks in document semantic segmentation has not yet been studied. Considering the nature of a recurrent neural network and the recent success of recurrent neural networks in document image binarization, it should be possible to employ a recurrent neural network for document semantic segmentation and further achieve high performance results. Objectives. The main objective of this thesis is to investigate if recurrent neural networks are a viable alternative to convolutional neural networks in document semantic segmentation. By using a combination of a convolutional neural network and a recurrent neural network, another objective is also to determine if the performance of the combination can improve upon the existing case of only using the recurrent neural network. Methods. To investigate the impact of recurrent neural networks in document semantic segmentation, three different recurrent neural network architectures are implemented and trained while their performance are further evaluated with Intersection over Union. Afterwards their segmentation result are compared to a convolutional neural network. By performing pre-processing on training images and multi-class labeling, prediction images are ultimately produced by the employed models. Results. The results from the gathered performance data shows a 2.7% performance difference between the best recurrent neural network model and the convolutional neural network. Notably, it can be observed that this recurrent neural network model has a more consistent performance than the convolutional neural network but comparable performance results overall. For the other recurrent neural network architectures lower performance results are observed which is connected to the complexity of these models. Furthermore, by analyzing the performance results of a model using a combination of a convolutional neural network and a recurrent neural network, it can be noticed that the combination performs significantly better with a 4.9% performance increase compared to the case with only using the recurrent neural network. Conclusions. This thesis concludes that recurrent neural networks are likely a viable alternative to convolutional neural networks in document semantic segmentation but that further investigation is required. Furthermore, by combining a convolutional neural network with a recurrent neural network it is concluded that the performance of a recurrent neural network model is…
Subjects/Keywords: semantic segmentation; page segmentation; recurrent neural network; layout analysis; semantisk segmentering; dokument segmentering; recurrent neural network; layout analys; Computer Sciences; Datavetenskap (datalogi)
Record Details
Similar Records
Cite
Share »
Record Details
Similar Records
Cite
« Share
❌
APA ·
Chicago ·
MLA ·
Vancouver ·
CSE |
Export
to Zotero / EndNote / Reference
Manager
APA (6th Edition):
Ahrneteg, J. (2019). Semantic Segmentation of Historical Document Images Using Recurrent Neural Networks. (Thesis). , Department of Software Engineering. Retrieved from http://urn.kb.se/resolve?urn=urn:nbn:se:bth-18219
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Chicago Manual of Style (16th Edition):
Ahrneteg, Jakob. “Semantic Segmentation of Historical Document Images Using Recurrent Neural Networks.” 2019. Thesis, , Department of Software Engineering. Accessed November 18, 2019.
http://urn.kb.se/resolve?urn=urn:nbn:se:bth-18219.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
MLA Handbook (7th Edition):
Ahrneteg, Jakob. “Semantic Segmentation of Historical Document Images Using Recurrent Neural Networks.” 2019. Web. 18 Nov 2019.
Vancouver:
Ahrneteg J. Semantic Segmentation of Historical Document Images Using Recurrent Neural Networks. [Internet] [Thesis]. , Department of Software Engineering; 2019. [cited 2019 Nov 18].
Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:bth-18219.
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
Council of Science Editors:
Ahrneteg J. Semantic Segmentation of Historical Document Images Using Recurrent Neural Networks. [Thesis]. , Department of Software Engineering; 2019. Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:bth-18219
Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
◁ [1] [2] [3] [4] ▶
. 
Open Access Theses and Dissertations