subject:(Deep learning)

Oregon State University

1. Ghaeini, Mohammad Reza. Event Detection with Forward-Backward Recurrent Neural Networks.

Degree: MS, 2017, Oregon State University

URL: http://hdl.handle.net/1957/61576

► Automatic event extraction from natural text is an important and challenging task for natural language understanding. Traditional event detection methods heavily rely on manually engineered… (more)

Subjects/Keywords: Deep Learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Ghaeini, M. R. (2017). Event Detection with Forward-Backward Recurrent Neural Networks. (Masters Thesis). Oregon State University. Retrieved from http://hdl.handle.net/1957/61576

Chicago Manual of Style (16^th Edition):

Ghaeini, Mohammad Reza. “Event Detection with Forward-Backward Recurrent Neural Networks.” 2017. Masters Thesis, Oregon State University. Accessed February 27, 2020. http://hdl.handle.net/1957/61576.

MLA Handbook (7^th Edition):

Ghaeini, Mohammad Reza. “Event Detection with Forward-Backward Recurrent Neural Networks.” 2017. Web. 27 Feb 2020.

Vancouver:

Ghaeini MR. Event Detection with Forward-Backward Recurrent Neural Networks. [Internet] [Masters thesis]. Oregon State University; 2017. [cited 2020 Feb 27]. Available from: http://hdl.handle.net/1957/61576.

Council of Science Editors:

Ghaeini MR. Event Detection with Forward-Backward Recurrent Neural Networks. [Masters Thesis]. Oregon State University; 2017. Available from: http://hdl.handle.net/1957/61576

University of Sydney

2. Windrim, Lloyd. Illumination Invariant Deep Learning for Hyperspectral Data .

Degree: 2018, University of Sydney

URL: http://hdl.handle.net/2123/18734

► Motivated by the variability in hyperspectral images due to illumination and the difficulty in acquiring labelled data, this thesis proposes different approaches for learning illumination… (more)

▼ Motivated by the variability in hyperspectral images due to illumination and the difficulty in acquiring labelled data, this thesis proposes different approaches for learning illumination invariant feature representations and classification models for hyperspectral data captured outdoors, under natural sunlight. The approaches integrate domain knowledge into learning algorithms and hence does not rely on a priori knowledge of atmospheric parameters, additional sensors or large amounts of labelled training data. Hyperspectral sensors record rich semantic information from a scene, making them useful for robotics or remote sensing applications where perception systems are used to gain an understanding of the scene. Images recorded by hyperspectral sensors can, however, be affected to varying degrees by intrinsic factors relating to the sensor itself (keystone, smile, noise, particularly at the limits of the sensed spectral range) but also by extrinsic factors such as the way the scene is illuminated. The appearance of the scene in the image is tied to the incident illumination which is dependent on variables such as the position of the sun, geometry of the surface and the prevailing atmospheric conditions. Effects like shadows can make the appearance and spectral characteristics of identical materials to be significantly different. This degrades the performance of high-level algorithms that use hyperspectral data, such as those that do classification and clustering. If sufficient training data is available, learning algorithms such as neural networks can capture variability in the scene appearance and be trained to compensate for it. Learning algorithms are advantageous for this task because they do not require a priori knowledge of the prevailing atmospheric conditions or data from additional sensors. Labelling of hyperspectral data is, however, difficult and time-consuming, so acquiring enough labelled samples for the learning algorithm to adequately capture the scene appearance is challenging. Hence, there is a need for the development of techniques that are invariant to the effects of illumination that do not require large amounts of labelled data. In this thesis, an approach to learning a representation of hyperspectral data that is invariant to the effects of illumination is proposed. This approach combines a physics-based model of the illumination process with an unsupervised deep learning algorithm, and thus requires no labelled data. Datasets that vary both temporally and spatially are used to compare the proposed approach to other similar state-of-the-art techniques. The results show that the learnt representation is more invariant to shadows in the image and to variations in brightness due to changes in the scene topography or position of the sun in the sky. The results also show that a supervised classifier can predict class labels more accurately and more consistently across time when images are represented using the proposed method. Additionally, this thesis proposes methods to train supervised…

Subjects/Keywords: Deep learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Windrim, L. (2018). Illumination Invariant Deep Learning for Hyperspectral Data . (Thesis). University of Sydney. Retrieved from http://hdl.handle.net/2123/18734

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Windrim, Lloyd. “Illumination Invariant Deep Learning for Hyperspectral Data .” 2018. Thesis, University of Sydney. Accessed February 27, 2020. http://hdl.handle.net/2123/18734.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Windrim, Lloyd. “Illumination Invariant Deep Learning for Hyperspectral Data .” 2018. Web. 27 Feb 2020.

Vancouver:

Windrim L. Illumination Invariant Deep Learning for Hyperspectral Data . [Internet] [Thesis]. University of Sydney; 2018. [cited 2020 Feb 27]. Available from: http://hdl.handle.net/2123/18734.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Windrim L. Illumination Invariant Deep Learning for Hyperspectral Data . [Thesis]. University of Sydney; 2018. Available from: http://hdl.handle.net/2123/18734

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Universidad de Cantabria

3. Noriega Puente, Andrea. Segmentación de gliomas en imagen de resonancia magnética multimodal: Glioma segmentation in multimodal magnetic resonance imaging.

Degree: Máster en Ciencia de Datos, 2019, Universidad de Cantabria

URL: http://hdl.handle.net/10902/17859

► RESUMEN: El glioma es el tipo de tumor cerebral más común, presentando distintos grados de malignidad y agresividad, así como un pronóstico variable. La gran… (more)

Subjects/Keywords: Deep Learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Noriega Puente, A. (2019). Segmentación de gliomas en imagen de resonancia magnética multimodal: Glioma segmentation in multimodal magnetic resonance imaging. (Masters Thesis). Universidad de Cantabria. Retrieved from http://hdl.handle.net/10902/17859

Chicago Manual of Style (16^th Edition):

Noriega Puente, Andrea. “Segmentación de gliomas en imagen de resonancia magnética multimodal: Glioma segmentation in multimodal magnetic resonance imaging.” 2019. Masters Thesis, Universidad de Cantabria. Accessed February 27, 2020. http://hdl.handle.net/10902/17859.

MLA Handbook (7^th Edition):

Noriega Puente, Andrea. “Segmentación de gliomas en imagen de resonancia magnética multimodal: Glioma segmentation in multimodal magnetic resonance imaging.” 2019. Web. 27 Feb 2020.

Vancouver:

Noriega Puente A. Segmentación de gliomas en imagen de resonancia magnética multimodal: Glioma segmentation in multimodal magnetic resonance imaging. [Internet] [Masters thesis]. Universidad de Cantabria; 2019. [cited 2020 Feb 27]. Available from: http://hdl.handle.net/10902/17859.

Council of Science Editors:

Noriega Puente A. Segmentación de gliomas en imagen de resonancia magnética multimodal: Glioma segmentation in multimodal magnetic resonance imaging. [Masters Thesis]. Universidad de Cantabria; 2019. Available from: http://hdl.handle.net/10902/17859

Cornell University

4. Sedra, Daniel. Training Paradigms For Deep Residual Networks .

Degree: 2016, Cornell University

URL: http://hdl.handle.net/1813/44294

► Convolutional networks are the current state of the art for image tasks. It has long been known that depth is key for increasing their expressive… (more)

Subjects/Keywords: deep learning; machine learning; deep residual networks

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Sedra, D. (2016). Training Paradigms For Deep Residual Networks . (Thesis). Cornell University. Retrieved from http://hdl.handle.net/1813/44294

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Sedra, Daniel. “Training Paradigms For Deep Residual Networks .” 2016. Thesis, Cornell University. Accessed February 27, 2020. http://hdl.handle.net/1813/44294.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Sedra, Daniel. “Training Paradigms For Deep Residual Networks .” 2016. Web. 27 Feb 2020.

Vancouver:

Sedra D. Training Paradigms For Deep Residual Networks . [Internet] [Thesis]. Cornell University; 2016. [cited 2020 Feb 27]. Available from: http://hdl.handle.net/1813/44294.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Sedra D. Training Paradigms For Deep Residual Networks . [Thesis]. Cornell University; 2016. Available from: http://hdl.handle.net/1813/44294

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Georgia Tech

5. Choi, Edward. Doctor AI: Interpretable deep learning for modeling electronic health records.

Degree: PhD, Computational Science and Engineering, 2018, Georgia Tech

URL: http://hdl.handle.net/1853/60226

► Deep learning recently has been showing superior performance in complex domains such as computer vision, audio processing and natural language processing compared to traditional statistical… (more)

Subjects/Keywords: Deep learning; Healthcare

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Choi, E. (2018). Doctor AI: Interpretable deep learning for modeling electronic health records. (Doctoral Dissertation). Georgia Tech. Retrieved from http://hdl.handle.net/1853/60226

Chicago Manual of Style (16^th Edition):

Choi, Edward. “Doctor AI: Interpretable deep learning for modeling electronic health records.” 2018. Doctoral Dissertation, Georgia Tech. Accessed February 27, 2020. http://hdl.handle.net/1853/60226.

MLA Handbook (7^th Edition):

Choi, Edward. “Doctor AI: Interpretable deep learning for modeling electronic health records.” 2018. Web. 27 Feb 2020.

Vancouver:

Choi E. Doctor AI: Interpretable deep learning for modeling electronic health records. [Internet] [Doctoral dissertation]. Georgia Tech; 2018. [cited 2020 Feb 27]. Available from: http://hdl.handle.net/1853/60226.

Council of Science Editors:

Choi E. Doctor AI: Interpretable deep learning for modeling electronic health records. [Doctoral Dissertation]. Georgia Tech; 2018. Available from: http://hdl.handle.net/1853/60226

University of KwaZulu-Natal

6. Govender, Lishen. Determination of quantum entanglement concurrence using multilayer perceptron neural networks.

Degree: 2017, University of KwaZulu-Natal

URL: http://hdl.handle.net/10413/15713

► Artificial Neural Networks, inspired by biological neural networks, have seen widespread implementations across all research areas in the past few years. This partly due to… (more)

Subjects/Keywords: Deep learning.; Machine learning.

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Govender, L. (2017). Determination of quantum entanglement concurrence using multilayer perceptron neural networks. (Thesis). University of KwaZulu-Natal. Retrieved from http://hdl.handle.net/10413/15713

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Govender, Lishen. “Determination of quantum entanglement concurrence using multilayer perceptron neural networks.” 2017. Thesis, University of KwaZulu-Natal. Accessed February 27, 2020. http://hdl.handle.net/10413/15713.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Govender, Lishen. “Determination of quantum entanglement concurrence using multilayer perceptron neural networks.” 2017. Web. 27 Feb 2020.

Vancouver:

Govender L. Determination of quantum entanglement concurrence using multilayer perceptron neural networks. [Internet] [Thesis]. University of KwaZulu-Natal; 2017. [cited 2020 Feb 27]. Available from: http://hdl.handle.net/10413/15713.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Govender L. Determination of quantum entanglement concurrence using multilayer perceptron neural networks. [Thesis]. University of KwaZulu-Natal; 2017. Available from: http://hdl.handle.net/10413/15713

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Illinois – Urbana-Champaign

7. Deshpande, Ishan. Generative modeling using the sliced Wasserstein distance.

Degree: MS, Electrical & Computer Engr, 2018, University of Illinois – Urbana-Champaign

URL: http://hdl.handle.net/2142/100951

► Generative adversarial nets (GANs) are very successful at modeling distributions from given samples, even in the high-dimensional case. However, their formulation is also known to… (more)

Subjects/Keywords: Machine Learning; Deep Learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Deshpande, I. (2018). Generative modeling using the sliced Wasserstein distance. (Thesis). University of Illinois – Urbana-Champaign. Retrieved from http://hdl.handle.net/2142/100951

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Deshpande, Ishan. “Generative modeling using the sliced Wasserstein distance.” 2018. Thesis, University of Illinois – Urbana-Champaign. Accessed February 27, 2020. http://hdl.handle.net/2142/100951.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Deshpande, Ishan. “Generative modeling using the sliced Wasserstein distance.” 2018. Web. 27 Feb 2020.

Vancouver:

Deshpande I. Generative modeling using the sliced Wasserstein distance. [Internet] [Thesis]. University of Illinois – Urbana-Champaign; 2018. [cited 2020 Feb 27]. Available from: http://hdl.handle.net/2142/100951.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Deshpande I. Generative modeling using the sliced Wasserstein distance. [Thesis]. University of Illinois – Urbana-Champaign; 2018. Available from: http://hdl.handle.net/2142/100951

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

California State University – Sacramento

8. Poosarla, Akshay. Bone age prediction with convolutional neural networks.

Degree: MS, Computer Science, 2019, California State University – Sacramento

URL: http://hdl.handle.net/10211.3/207660

► Skeletal bone age assessment is a common clinical practice to analyze and assess the biological maturity of pediatric patients. This process generally involves taking X-ray… (more)

Subjects/Keywords: Machine learning; Deep learning; Boneage

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Poosarla, A. (2019). Bone age prediction with convolutional neural networks. (Masters Thesis). California State University – Sacramento. Retrieved from http://hdl.handle.net/10211.3/207660

Chicago Manual of Style (16^th Edition):

Poosarla, Akshay. “Bone age prediction with convolutional neural networks.” 2019. Masters Thesis, California State University – Sacramento. Accessed February 27, 2020. http://hdl.handle.net/10211.3/207660.

MLA Handbook (7^th Edition):

Poosarla, Akshay. “Bone age prediction with convolutional neural networks.” 2019. Web. 27 Feb 2020.

Vancouver:

Poosarla A. Bone age prediction with convolutional neural networks. [Internet] [Masters thesis]. California State University – Sacramento; 2019. [cited 2020 Feb 27]. Available from: http://hdl.handle.net/10211.3/207660.

Council of Science Editors:

Poosarla A. Bone age prediction with convolutional neural networks. [Masters Thesis]. California State University – Sacramento; 2019. Available from: http://hdl.handle.net/10211.3/207660

Cornell University

9. Lenz, Ian. Deep Learning For Robotics .

Degree: 2016, Cornell University

URL: http://hdl.handle.net/1813/44317

► Robotics faces many unique challenges as robotic platforms move out of the lab and into the real world. In particular, the huge amount of variety… (more)

Subjects/Keywords: Robotics; Machine learning; Deep learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Lenz, I. (2016). Deep Learning For Robotics . (Thesis). Cornell University. Retrieved from http://hdl.handle.net/1813/44317

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Lenz, Ian. “Deep Learning For Robotics .” 2016. Thesis, Cornell University. Accessed February 27, 2020. http://hdl.handle.net/1813/44317.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Lenz, Ian. “Deep Learning For Robotics .” 2016. Web. 27 Feb 2020.

Vancouver:

Lenz I. Deep Learning For Robotics . [Internet] [Thesis]. Cornell University; 2016. [cited 2020 Feb 27]. Available from: http://hdl.handle.net/1813/44317.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Lenz I. Deep Learning For Robotics . [Thesis]. Cornell University; 2016. Available from: http://hdl.handle.net/1813/44317

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Illinois – Urbana-Champaign

10. Liu, Jialin. Machine learning workflow optimization via automatic discovery of resource reuse opportunities.

Degree: MS, Computer Science, 2019, University of Illinois – Urbana-Champaign

URL: http://hdl.handle.net/2142/104894

► Many state-of-the-art deep learning models rely on dynamic computation logic, making them difﬁcult to optimize. In this thesis, we present a hashing based algorithm that… (more)

Subjects/Keywords: Machine Learning; Deep Learning; System

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Liu, J. (2019). Machine learning workflow optimization via automatic discovery of resource reuse opportunities. (Thesis). University of Illinois – Urbana-Champaign. Retrieved from http://hdl.handle.net/2142/104894

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Liu, Jialin. “Machine learning workflow optimization via automatic discovery of resource reuse opportunities.” 2019. Thesis, University of Illinois – Urbana-Champaign. Accessed February 27, 2020. http://hdl.handle.net/2142/104894.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Liu, Jialin. “Machine learning workflow optimization via automatic discovery of resource reuse opportunities.” 2019. Web. 27 Feb 2020.

Vancouver:

Liu J. Machine learning workflow optimization via automatic discovery of resource reuse opportunities. [Internet] [Thesis]. University of Illinois – Urbana-Champaign; 2019. [cited 2020 Feb 27]. Available from: http://hdl.handle.net/2142/104894.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Liu J. Machine learning workflow optimization via automatic discovery of resource reuse opportunities. [Thesis]. University of Illinois – Urbana-Champaign; 2019. Available from: http://hdl.handle.net/2142/104894

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Princeton University

11. Ravi, Sachin. Meta-Learning for Data and Processing Efficiency .

Degree: PhD, 2019, Princeton University

URL: http://arks.princeton.edu/ark:/88435/dsp013j333513x

► Deep learning models have shown great success in a variety of machine learning benchmarks; however, these models still lack the efficiency and flexibility of humans.… (more)

▼ Deep learning models have shown great success in a variety of machine learning benchmarks; however, these models still lack the efficiency and flexibility of humans. Current deep learning methods involve training on a large amount of data to produce a model that can then specialize to the specific task encoded by the training data. Humans, on the other hand, are able to learn new concepts throughout our lives with comparatively little feedback. In order to bridge this gap, previous work has suggested the use of meta-learning. Rather than learning how to do a specific task, meta-learning involves learning how-to-learn and utilizing this knowledge to learn new tasks more effectively. This thesis focuses on using meta-learning to improve the data and processing efficiency of deep learning models when learning new tasks. First, we discuss a meta-learning model for the few-shot learning problem, where the aim is to learn a new classification task having unseen classes with few labeled examples. We use a LSTM-based meta-learner model to learn both the initialization and the optimization algorithm used to train another neural network and show that our method compares favorably to nearest-neighbor approaches. The second part of the thesis deals with improving the predictive uncertainty of models in the few-shot learning setting. Using a Bayesian perspective, we propose a meta-learning method which efficiently amortizes hierarchical variational inference across tasks, learning a prior distribution over neural network weights so that a few steps of gradient descent will produce a good task-specific approximate posterior. Finally, we focus on applying meta-learning in the context of making choices that impact processing efficacy. When training a network on multiple tasks, we have a choice between interactive parallelism (training on different tasks one after another) and independent parallelism (using the network to process multiple tasks concurrently). For the simulation environment considered, we show that there is a trade-off between these two types of processing choices in deep neural networks. We then discuss a meta-learning algorithm for an agent to learn how to train itself with regard to this trade-off in an environment with unknown serialization cost. Advisors/Committee Members: Li, Kai (advisor).

Subjects/Keywords: Deep Learning; Meta-Learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Ravi, S. (2019). Meta-Learning for Data and Processing Efficiency . (Doctoral Dissertation). Princeton University. Retrieved from http://arks.princeton.edu/ark:/88435/dsp013j333513x

Chicago Manual of Style (16^th Edition):

Ravi, Sachin. “Meta-Learning for Data and Processing Efficiency .” 2019. Doctoral Dissertation, Princeton University. Accessed February 27, 2020. http://arks.princeton.edu/ark:/88435/dsp013j333513x.

MLA Handbook (7^th Edition):

Ravi, Sachin. “Meta-Learning for Data and Processing Efficiency .” 2019. Web. 27 Feb 2020.

Vancouver:

Ravi S. Meta-Learning for Data and Processing Efficiency . [Internet] [Doctoral dissertation]. Princeton University; 2019. [cited 2020 Feb 27]. Available from: http://arks.princeton.edu/ark:/88435/dsp013j333513x.

Council of Science Editors:

Ravi S. Meta-Learning for Data and Processing Efficiency . [Doctoral Dissertation]. Princeton University; 2019. Available from: http://arks.princeton.edu/ark:/88435/dsp013j333513x

Australian National University

12. Dong, Cong. Spatial Deep Networks for Outdoor Scene Classification .

Degree: 2015, Australian National University

URL: http://hdl.handle.net/1885/101712

► Scene classification has become an increasingly popular topic in computer vision. The techniques for scene classification can be widely used in many other aspects, such… (more)

▼ Scene classification has become an increasingly popular topic in computer vision. The techniques for scene classification can be widely used in many other aspects, such as detection, action recognition, and content-based image retrieval. Recently, the stationary property of images has been leveraged in conjunction with convolutional networks to perform classification tasks. In the existing approach, one random patch is extracted from each training image to learn filters for convolutional processes. However, feature learning only from one random patch per image is not robust because patches selected from di↵erent areas of an image may contain distinct scene objects which make the features of these patches have di↵erent descriptive power. In this dissertation, focusing on deep learning techniques, we propose a multi-scale network that utilizes multiple random patches and di↵erent patch dimensions to learn feature representations for images in order to improve the existing approach. Despite the much better performance the multi-scale network can achieve than the existing approach, lacking of local features and the spatial layout is one of the core limitations of both methods. Therefore, we propose a novel Spatial Deep Network (SDN) to further enhance the existing approach by exploiting the spatial layout of the image and constraining the random patch extraction to be performed in di↵erent areas of the image so as to e↵ectively restrict the patches to hold the necessary characteristics of di↵erent image areas. In this way, SDN yields compact but discriminative features that incorporate both global descriptors and the local spatial information for images. Experiment results show that SDN considerably exceeds the existing approach and multi-scale networks and achieves competitive performance with some widely used classification techniques on the OT dataset (developed by Oliva and Torralba). In order to evaluate the robustness of the proposed SDN, we also apply it to the content-based image retrieval on the Holidays dataset, where our features attain much better retrieval performance but have much lower feature dimensions compared to other state-of-the-art feature descriptors.

Subjects/Keywords: Deep Learning; Scene Classification; Spatial Deep Networks

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Dong, C. (2015). Spatial Deep Networks for Outdoor Scene Classification . (Thesis). Australian National University. Retrieved from http://hdl.handle.net/1885/101712

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Dong, Cong. “Spatial Deep Networks for Outdoor Scene Classification .” 2015. Thesis, Australian National University. Accessed February 27, 2020. http://hdl.handle.net/1885/101712.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Dong, Cong. “Spatial Deep Networks for Outdoor Scene Classification .” 2015. Web. 27 Feb 2020.

Vancouver:

Dong C. Spatial Deep Networks for Outdoor Scene Classification . [Internet] [Thesis]. Australian National University; 2015. [cited 2020 Feb 27]. Available from: http://hdl.handle.net/1885/101712.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Dong C. Spatial Deep Networks for Outdoor Scene Classification . [Thesis]. Australian National University; 2015. Available from: http://hdl.handle.net/1885/101712

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Guelph

13. Im, Jiwoong. Analyzing Unsupervised Representation Learning Models Under the View of Dynamical Systems .

Degree: 2015, University of Guelph

URL: https://atrium.lib.uoguelph.ca/xmlui/handle/10214/8809

► The objective of this thesis is to take the dynamical systems approach to understand the unsupervised learning models and learning algorithms. Gated auto-encoders (GAEs) are… (more)

Subjects/Keywords: Machine learning; Deep Learning; unsupervised learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Im, J. (2015). Analyzing Unsupervised Representation Learning Models Under the View of Dynamical Systems . (Thesis). University of Guelph. Retrieved from https://atrium.lib.uoguelph.ca/xmlui/handle/10214/8809

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Im, Jiwoong. “Analyzing Unsupervised Representation Learning Models Under the View of Dynamical Systems .” 2015. Thesis, University of Guelph. Accessed February 27, 2020. https://atrium.lib.uoguelph.ca/xmlui/handle/10214/8809.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Im, Jiwoong. “Analyzing Unsupervised Representation Learning Models Under the View of Dynamical Systems .” 2015. Web. 27 Feb 2020.

Vancouver:

Im J. Analyzing Unsupervised Representation Learning Models Under the View of Dynamical Systems . [Internet] [Thesis]. University of Guelph; 2015. [cited 2020 Feb 27]. Available from: https://atrium.lib.uoguelph.ca/xmlui/handle/10214/8809.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Im J. Analyzing Unsupervised Representation Learning Models Under the View of Dynamical Systems . [Thesis]. University of Guelph; 2015. Available from: https://atrium.lib.uoguelph.ca/xmlui/handle/10214/8809

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Waterloo

14. Gaurav, Ashish. Safety-Oriented Stability Biases for Continual Learning.

Degree: 2020, University of Waterloo

URL: http://hdl.handle.net/10012/15579

► Continual learning is often confounded by “catastrophic forgetting” that prevents neural networks from learning tasks sequentially. In the case of real world classification systems that… (more)

Subjects/Keywords: deep learning; continual learning; classification; reinforcement learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Gaurav, A. (2020). Safety-Oriented Stability Biases for Continual Learning. (Thesis). University of Waterloo. Retrieved from http://hdl.handle.net/10012/15579

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Gaurav, Ashish. “Safety-Oriented Stability Biases for Continual Learning.” 2020. Thesis, University of Waterloo. Accessed February 27, 2020. http://hdl.handle.net/10012/15579.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Gaurav, Ashish. “Safety-Oriented Stability Biases for Continual Learning.” 2020. Web. 27 Feb 2020.

Vancouver:

Gaurav A. Safety-Oriented Stability Biases for Continual Learning. [Internet] [Thesis]. University of Waterloo; 2020. [cited 2020 Feb 27]. Available from: http://hdl.handle.net/10012/15579.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Gaurav A. Safety-Oriented Stability Biases for Continual Learning. [Thesis]. University of Waterloo; 2020. Available from: http://hdl.handle.net/10012/15579

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

NSYSU

15. Lin, Kun-da. Deep Reinforcement Learning with a Gating Network.

Degree: Master, Electrical Engineering, 2017, NSYSU

URL: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0223117-131536

► Reinforcement Learning (RL) is a good way to train the robot since it doesn't need an exact model of the environment. All need is to… (more)

▼ Reinforcement Learning (RL) is a good way to train the robot since it doesn't need an exact model of the environment. All need is to let a learning agent interact with the en-vironment by an appropriate reward function, which is associated with the goal of the task that the agent is expected to accomplish. Unfortunately, itâs hard to learn a diffi-cult reward function for a complicated problem, such as a soccer player in the game where the goal of scoring is not directly related to the mission or the role the player is asked to play by the coach. Besides, the tabular method for approximation of returns in RL is more suitable for an environment with less states. In a huge state space, RL methods always face the curse of dimensionality. To alleviate those difficulties, this paper proposed an algorithm â a deep reinforcement learning method regulated by and gating networks. By the merit of deep learning neural networks, even regarding pixels in an image as states, the latent features can be trained and implicitly extracted layer by layer from raw data. In the proposed method, a composed policy can be obtained by a gating network which regulates the outputs from several deep learning modules, each of which is trained for an individual policy. In this thesis, two video games, flappy bird, and ping-pong is adopted as the testbeds to examinate the performance of the proposed method. In the proposed architecture, each policy module of deep learning is trained by a simple reward functions first. By the gating networks, these simple policies can be composed into a more sophisticated one, so as to accommodate with more complicated tasks. This is akin to the divide-and-conquer strategy. The proposed architecture has two kinds of arrangements and structures. One is called the in-parallel gating network, and the other is called the in-serial network. From the outcomes, itâs observed that both can efficiently shorten the training time. Advisors/Committee Members: Ming-Yi Ju (chair), Yu-Jen Chen (chair), Kao-Shing Hwang (committee member), Jin-Ling Lin (chair).

Subjects/Keywords: Reinforcement Learning; Deep Reinforcement Learning; Deep Learning; Gating network; Neural network

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Lin, K. (2017). Deep Reinforcement Learning with a Gating Network. (Thesis). NSYSU. Retrieved from http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0223117-131536

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Lin, Kun-da. “Deep Reinforcement Learning with a Gating Network.” 2017. Thesis, NSYSU. Accessed February 27, 2020. http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0223117-131536.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Lin, Kun-da. “Deep Reinforcement Learning with a Gating Network.” 2017. Web. 27 Feb 2020.

Vancouver:

Lin K. Deep Reinforcement Learning with a Gating Network. [Internet] [Thesis]. NSYSU; 2017. [cited 2020 Feb 27]. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0223117-131536.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Lin K. Deep Reinforcement Learning with a Gating Network. [Thesis]. NSYSU; 2017. Available from: http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0223117-131536

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Illinois – Urbana-Champaign

16. Liang, Shiyu. Why deep neural networks for function approximation.

Degree: MS, Electrical & Computer Engr, 2017, University of Illinois – Urbana-Champaign

URL: http://hdl.handle.net/2142/99417

► Recently there has been much interest in understanding why deep neural networks are preferred to shallow networks. We show that, for a large class of… (more)

Subjects/Keywords: Neural networks; Deep learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Liang, S. (2017). Why deep neural networks for function approximation. (Thesis). University of Illinois – Urbana-Champaign. Retrieved from http://hdl.handle.net/2142/99417

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Liang, Shiyu. “Why deep neural networks for function approximation.” 2017. Thesis, University of Illinois – Urbana-Champaign. Accessed February 27, 2020. http://hdl.handle.net/2142/99417.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Liang, Shiyu. “Why deep neural networks for function approximation.” 2017. Web. 27 Feb 2020.

Vancouver:

Liang S. Why deep neural networks for function approximation. [Internet] [Thesis]. University of Illinois – Urbana-Champaign; 2017. [cited 2020 Feb 27]. Available from: http://hdl.handle.net/2142/99417.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Liang S. Why deep neural networks for function approximation. [Thesis]. University of Illinois – Urbana-Champaign; 2017. Available from: http://hdl.handle.net/2142/99417

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

University of Illinois – Urbana-Champaign

17. Yeh, Raymond Alexander. Stable and symmetric convolutional neural network.

Degree: MS, Electrical & Computer Engr, 2016, University of Illinois – Urbana-Champaign

URL: http://hdl.handle.net/2142/92687

► First we present a proof that convolutional neural networks (CNNs) with max-norm regularization, max-pooling, and Relu non-linearity are stable to additive noise. Second, we explore… (more)

Subjects/Keywords: convolutional neural network; deep learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Yeh, R. A. (2016). Stable and symmetric convolutional neural network. (Thesis). University of Illinois – Urbana-Champaign. Retrieved from http://hdl.handle.net/2142/92687

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Yeh, Raymond Alexander. “Stable and symmetric convolutional neural network.” 2016. Thesis, University of Illinois – Urbana-Champaign. Accessed February 27, 2020. http://hdl.handle.net/2142/92687.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Yeh, Raymond Alexander. “Stable and symmetric convolutional neural network.” 2016. Web. 27 Feb 2020.

Vancouver:

Yeh RA. Stable and symmetric convolutional neural network. [Internet] [Thesis]. University of Illinois – Urbana-Champaign; 2016. [cited 2020 Feb 27]. Available from: http://hdl.handle.net/2142/92687.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Yeh RA. Stable and symmetric convolutional neural network. [Thesis]. University of Illinois – Urbana-Champaign; 2016. Available from: http://hdl.handle.net/2142/92687

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Rochester Institute of Technology

18. Petroski Such, Felipe. Deep Learning Architectures for Novel Problems.

Degree: MS, Computer Engineering, 2017, Rochester Institute of Technology

URL: https://scholarworks.rit.edu/theses/9611

► With convolutional neural networks revolutionizing the computer vision field it is important to extend the capabilities of neural-based systems to dynamic and unrestricted data… (more)

Subjects/Keywords: Deep learning; ICR; Machine intelligence

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Petroski Such, F. (2017). Deep Learning Architectures for Novel Problems. (Masters Thesis). Rochester Institute of Technology. Retrieved from https://scholarworks.rit.edu/theses/9611

Chicago Manual of Style (16^th Edition):

Petroski Such, Felipe. “Deep Learning Architectures for Novel Problems.” 2017. Masters Thesis, Rochester Institute of Technology. Accessed February 27, 2020. https://scholarworks.rit.edu/theses/9611.

MLA Handbook (7^th Edition):

Petroski Such, Felipe. “Deep Learning Architectures for Novel Problems.” 2017. Web. 27 Feb 2020.

Vancouver:

Petroski Such F. Deep Learning Architectures for Novel Problems. [Internet] [Masters thesis]. Rochester Institute of Technology; 2017. [cited 2020 Feb 27]. Available from: https://scholarworks.rit.edu/theses/9611.

Council of Science Editors:

Petroski Such F. Deep Learning Architectures for Novel Problems. [Masters Thesis]. Rochester Institute of Technology; 2017. Available from: https://scholarworks.rit.edu/theses/9611

Rochester Institute of Technology

19. Lamos-Sweeney, Joshua. Deep learning using genetic algorithms.

Degree: Computer Science (GCCIS), 2012, Rochester Institute of Technology

URL: https://scholarworks.rit.edu/theses/254

► Deep Learning networks are a new type of neural network that discovers important object features. These networks determine features without supervision, and are adept at… (more)

Subjects/Keywords: Deep learning; Genetic algorithms

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Lamos-Sweeney, J. (2012). Deep learning using genetic algorithms. (Thesis). Rochester Institute of Technology. Retrieved from https://scholarworks.rit.edu/theses/254

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Lamos-Sweeney, Joshua. “Deep learning using genetic algorithms.” 2012. Thesis, Rochester Institute of Technology. Accessed February 27, 2020. https://scholarworks.rit.edu/theses/254.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Lamos-Sweeney, Joshua. “Deep learning using genetic algorithms.” 2012. Web. 27 Feb 2020.

Vancouver:

Lamos-Sweeney J. Deep learning using genetic algorithms. [Internet] [Thesis]. Rochester Institute of Technology; 2012. [cited 2020 Feb 27]. Available from: https://scholarworks.rit.edu/theses/254.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Lamos-Sweeney J. Deep learning using genetic algorithms. [Thesis]. Rochester Institute of Technology; 2012. Available from: https://scholarworks.rit.edu/theses/254

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Penn State University

20. Lageman, Nathaniel John. BinDNN: Resilient Function Matching Using Deep Learning.

Degree: MS, Computer Science and Engineering, 2016, Penn State University

URL: https://etda.libraries.psu.edu/catalog/12477njl5114

► Determining if two functions taken from different compiled binaries originate from the same function in the source code has many applications to malware reverse engineering.… (more)

Subjects/Keywords: reverse engineering; malware; deep learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Lageman, N. J. (2016). BinDNN: Resilient Function Matching Using Deep Learning. (Masters Thesis). Penn State University. Retrieved from https://etda.libraries.psu.edu/catalog/12477njl5114

Chicago Manual of Style (16^th Edition):

Lageman, Nathaniel John. “BinDNN: Resilient Function Matching Using Deep Learning.” 2016. Masters Thesis, Penn State University. Accessed February 27, 2020. https://etda.libraries.psu.edu/catalog/12477njl5114.

MLA Handbook (7^th Edition):

Lageman, Nathaniel John. “BinDNN: Resilient Function Matching Using Deep Learning.” 2016. Web. 27 Feb 2020.

Vancouver:

Lageman NJ. BinDNN: Resilient Function Matching Using Deep Learning. [Internet] [Masters thesis]. Penn State University; 2016. [cited 2020 Feb 27]. Available from: https://etda.libraries.psu.edu/catalog/12477njl5114.

Council of Science Editors:

Lageman NJ. BinDNN: Resilient Function Matching Using Deep Learning. [Masters Thesis]. Penn State University; 2016. Available from: https://etda.libraries.psu.edu/catalog/12477njl5114

Penn State University

21. Papernot, Nicolas. On The Integrity Of Deep Learning Systems In Adversarial Settings.

Degree: MS, Computer Science and Engineering, 2016, Penn State University

URL: https://etda.libraries.psu.edu/catalog/28680

► Deep learning takes advantage of large datasets and computationally efficient training algorithms to outperform other approaches at various machine learning tasks. However, imperfections in the… (more)

Subjects/Keywords: computer security; deep learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Papernot, N. (2016). On The Integrity Of Deep Learning Systems In Adversarial Settings. (Masters Thesis). Penn State University. Retrieved from https://etda.libraries.psu.edu/catalog/28680

Chicago Manual of Style (16^th Edition):

Papernot, Nicolas. “On The Integrity Of Deep Learning Systems In Adversarial Settings.” 2016. Masters Thesis, Penn State University. Accessed February 27, 2020. https://etda.libraries.psu.edu/catalog/28680.

MLA Handbook (7^th Edition):

Papernot, Nicolas. “On The Integrity Of Deep Learning Systems In Adversarial Settings.” 2016. Web. 27 Feb 2020.

Vancouver:

Papernot N. On The Integrity Of Deep Learning Systems In Adversarial Settings. [Internet] [Masters thesis]. Penn State University; 2016. [cited 2020 Feb 27]. Available from: https://etda.libraries.psu.edu/catalog/28680.

Council of Science Editors:

Papernot N. On The Integrity Of Deep Learning Systems In Adversarial Settings. [Masters Thesis]. Penn State University; 2016. Available from: https://etda.libraries.psu.edu/catalog/28680

University of Manchester

22. Salman, Ahmad. Learning speaker-specific characteristics with deep neural architecture.

Degree: PhD, 2012, University of Manchester

URL: https://www.research.manchester.ac.uk/portal/en/theses/learning-speakerspecific-characteristics-with-deep-neural-architecture(24acb31d-2106-4e52-80ab-6c649838026a).html ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.558060

► Robust Speaker Recognition (SR) has been a focus of attention for researchers since long. The advancement in speech-aided technologies especially biometrics highlights the necessity of… (more)

▼ Robust Speaker Recognition (SR) has been a focus of attention for researchers since long. The advancement in speech-aided technologies especially biometrics highlights the necessity of foolproof SR systems. However, the performance of a SR system critically depends on the quality of speech features used to represent the speaker-specific information. This research aims at extracting the speaker-specific information from Mel-frequency Cepstral Coefficients (MFCCs) using deep learning. Speech is a mixture of various information components that include linguistic, speaker-specific and speaker’s emotional state information. Feature extraction for each information component is inevitable in different speech-related tasks for robust performance. However, almost all forms of speech representation carry all the information as a whole, which is responsible for the compromised performances by SR systems. Motivated by the complex problem solving ability of deep architectures by learning high-level task-specific information in the data, we propose a novel Deep Neural Architecture (DNA) to extract speaker-specific information (SI) from MFCCs, a popular frequency domain speech signal representation. A two-stage learning strategy is adopted, which is based on unsupervised training for network initialisation followed by regularised contrastive learning. To train our network in the 2nd stage, we devise a contrastive loss function to discriminate the speakers on the basis of their intrinsic statistical patterns, distributed in the representations yielded by our deep network. This is achieved in the contrastive pair-wise comparison of these representations for similar or dissimilar speakers. To improve the generalisation and reduce the interference of environmental effects with the speaker-specific representation, we regulate the contrastive loss with the data reconstruction loss in a multi-objective optimisation. A detailed study has been done to analyse the parametric space in training the proposed deep architecture for optimum performance. Finally we compare the performance of our learned speaker-specific representations with several state-of-the-art techniques in speaker verification and speaker segmentation tasks. It is evident that the representations acquired through learned DNA are invariant and comparatively less sensitive to the text, language and environmental variability.

Subjects/Keywords: 006.4; Speaker Recognition; Deep Learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Salman, A. (2012). Learning speaker-specific characteristics with deep neural architecture. (Doctoral Dissertation). University of Manchester. Retrieved from https://www.research.manchester.ac.uk/portal/en/theses/learning-speakerspecific-characteristics-with-deep-neural-architecture(24acb31d-2106-4e52-80ab-6c649838026a).html ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.558060

Chicago Manual of Style (16^th Edition):

Salman, Ahmad. “Learning speaker-specific characteristics with deep neural architecture.” 2012. Doctoral Dissertation, University of Manchester. Accessed February 27, 2020. https://www.research.manchester.ac.uk/portal/en/theses/learning-speakerspecific-characteristics-with-deep-neural-architecture(24acb31d-2106-4e52-80ab-6c649838026a).html ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.558060.

MLA Handbook (7^th Edition):

Salman, Ahmad. “Learning speaker-specific characteristics with deep neural architecture.” 2012. Web. 27 Feb 2020.

Vancouver:

Salman A. Learning speaker-specific characteristics with deep neural architecture. [Internet] [Doctoral dissertation]. University of Manchester; 2012. [cited 2020 Feb 27]. Available from: https://www.research.manchester.ac.uk/portal/en/theses/learning-speakerspecific-characteristics-with-deep-neural-architecture(24acb31d-2106-4e52-80ab-6c649838026a).html ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.558060.

Council of Science Editors:

Salman A. Learning speaker-specific characteristics with deep neural architecture. [Doctoral Dissertation]. University of Manchester; 2012. Available from: https://www.research.manchester.ac.uk/portal/en/theses/learning-speakerspecific-characteristics-with-deep-neural-architecture(24acb31d-2106-4e52-80ab-6c649838026a).html ; http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.558060

University of Otago

23. Szymanski, Lech. Deep architectures and classification by intermediary transformations .

Degree: 2012, University of Otago

URL: http://hdl.handle.net/10523/2129

► With the development of deep belief nets, the empirical evidence supporting a link between deep architecture neural networks and generalisation with respect to classification has… (more)

Subjects/Keywords: Machine learning; Classification; Deep architectures

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Szymanski, L. (2012). Deep architectures and classification by intermediary transformations . (Doctoral Dissertation). University of Otago. Retrieved from http://hdl.handle.net/10523/2129

Chicago Manual of Style (16^th Edition):

Szymanski, Lech. “Deep architectures and classification by intermediary transformations .” 2012. Doctoral Dissertation, University of Otago. Accessed February 27, 2020. http://hdl.handle.net/10523/2129.

MLA Handbook (7^th Edition):

Szymanski, Lech. “Deep architectures and classification by intermediary transformations .” 2012. Web. 27 Feb 2020.

Vancouver:

Szymanski L. Deep architectures and classification by intermediary transformations . [Internet] [Doctoral dissertation]. University of Otago; 2012. [cited 2020 Feb 27]. Available from: http://hdl.handle.net/10523/2129.

Council of Science Editors:

Szymanski L. Deep architectures and classification by intermediary transformations . [Doctoral Dissertation]. University of Otago; 2012. Available from: http://hdl.handle.net/10523/2129

University of Illinois – Urbana-Champaign

24. Wang, Zhangyang. Task-specific and interpretable feature learning.

Degree: PhD, Electrical & Computer Engr, 2016, University of Illinois – Urbana-Champaign

URL: http://hdl.handle.net/2142/95560

► Deep learning models have had tremendous impacts in recent years, while a question has been raised by many: Is deep learning just a triumph of… (more)

▼ Deep learning models have had tremendous impacts in recent years, while a question has been raised by many: Is deep learning just a triumph of empiricism? There has been emerging interest in reducing the gap between the theoretical soundness and interpretability, and the empirical success of deep models. This dissertation provides a comprehensive discussion on bridging traditional model-based learning approaches that emphasize problem-specific reasoning, and deep models that allow for larger learning capacity. The overall goal is to devise the next-generation feature learning architectures that are: 1) task-specific, namely, optimizing the entire pipeline from end to end while taking advantage of available prior knowledge and domain expertise; and 2) interpretable, namely, being able to learn a representation consisting of semantically sensible variables, and to display predictable behaviors. This dissertation starts by showing how the classical sparse coding models could be improved in a task-specific way, by formulating the entire pipeline as bi-level optimization. Then, it mainly illustrates how to incorporate the structure of classical learning models, e.g., sparse coding, into the design of deep architectures. A few concrete model examples are presented, ranging from the ℓ₀ and ℓ₁ sparse approximation models, to the ℓ_∞ constrained model and the dual-sparsity model. The analytic tools in the optimization problems can be translated to guide the architecture design and performance analysis of deep models. As a result, those customized deep models demonstrate improved performance, intuitive interpretation, and efficient parameter initialization. On the other hand, deep networks are shown to be analogous to brain mechanisms. They exhibit the ability to describe semantic content from the primitive level to the abstract level. This dissertation thus also presents a preliminary investigation of the synergy between feature learning with cognitive science and neuroscience. Two novel application domains, image aesthetics assessment and brain encoding, are explored, with promising preliminary results achieved. Advisors/Committee Members: Huang, Thomas (advisor), Huang, Thomas (Committee Chair), Hasegawa-Johnson, Mark (committee member), Liang, Zhi-Pei (committee member), Dolcos, Florin (committee member), Yang, Jianchao (committee member).

Subjects/Keywords: deep learning; sparse representation

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Wang, Z. (2016). Task-specific and interpretable feature learning. (Doctoral Dissertation). University of Illinois – Urbana-Champaign. Retrieved from http://hdl.handle.net/2142/95560

Chicago Manual of Style (16^th Edition):

Wang, Zhangyang. “Task-specific and interpretable feature learning.” 2016. Doctoral Dissertation, University of Illinois – Urbana-Champaign. Accessed February 27, 2020. http://hdl.handle.net/2142/95560.

MLA Handbook (7^th Edition):

Wang, Zhangyang. “Task-specific and interpretable feature learning.” 2016. Web. 27 Feb 2020.

Vancouver:

Wang Z. Task-specific and interpretable feature learning. [Internet] [Doctoral dissertation]. University of Illinois – Urbana-Champaign; 2016. [cited 2020 Feb 27]. Available from: http://hdl.handle.net/2142/95560.

Council of Science Editors:

Wang Z. Task-specific and interpretable feature learning. [Doctoral Dissertation]. University of Illinois – Urbana-Champaign; 2016. Available from: http://hdl.handle.net/2142/95560

25. Furusho, Yasutaka. Roles of Pre-training in Deep Neural Networks from Information Theoretical Perspective : Pre-trainingがニューラルネットワークに与える影響の情報理論的解析; Pre-training ガニューラルネットワークニアタエルエイキョウノジョウホウリロンテキカイセキ.

Degree: Nara Institute of Science and Technology / 奈良先端科学技術大学院大学

URL: http://hdl.handle.net/10061/11622

Subjects/Keywords: deep learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Furusho, Y. (n.d.). Roles of Pre-training in Deep Neural Networks from Information Theoretical Perspective : Pre-trainingがニューラルネットワークに与える影響の情報理論的解析; Pre-training ガニューラルネットワークニアタエルエイキョウノジョウホウリロンテキカイセキ. (Thesis). Nara Institute of Science and Technology / 奈良先端科学技術大学院大学. Retrieved from http://hdl.handle.net/10061/11622

Note: this citation may be lacking information needed for this citation format:
No year of publication.
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Furusho, Yasutaka. “Roles of Pre-training in Deep Neural Networks from Information Theoretical Perspective : Pre-trainingがニューラルネットワークに与える影響の情報理論的解析; Pre-training ガニューラルネットワークニアタエルエイキョウノジョウホウリロンテキカイセキ.” Thesis, Nara Institute of Science and Technology / 奈良先端科学技術大学院大学. Accessed February 27, 2020. http://hdl.handle.net/10061/11622.

Note: this citation may be lacking information needed for this citation format:
No year of publication.
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Furusho, Yasutaka. “Roles of Pre-training in Deep Neural Networks from Information Theoretical Perspective : Pre-trainingがニューラルネットワークに与える影響の情報理論的解析; Pre-training ガニューラルネットワークニアタエルエイキョウノジョウホウリロンテキカイセキ.” Web. 27 Feb 2020.

Note: this citation may be lacking information needed for this citation format:
No year of publication.

Vancouver:

Furusho Y. Roles of Pre-training in Deep Neural Networks from Information Theoretical Perspective : Pre-trainingがニューラルネットワークに与える影響の情報理論的解析; Pre-training ガニューラルネットワークニアタエルエイキョウノジョウホウリロンテキカイセキ. [Internet] [Thesis]. Nara Institute of Science and Technology / 奈良先端科学技術大学院大学; [cited 2020 Feb 27]. Available from: http://hdl.handle.net/10061/11622.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
No year of publication.

Council of Science Editors:

Furusho Y. Roles of Pre-training in Deep Neural Networks from Information Theoretical Perspective : Pre-trainingがニューラルネットワークに与える影響の情報理論的解析; Pre-training ガニューラルネットワークニアタエルエイキョウノジョウホウリロンテキカイセキ. [Thesis]. Nara Institute of Science and Technology / 奈良先端科学技術大学院大学; Available from: http://hdl.handle.net/10061/11622

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation
No year of publication.

McMaster University

26. Liu, Zheng. Generic Model-Agnostic Convolutional Neural Networks for Single Image Dehazing.

Degree: MASc, 2018, McMaster University

URL: http://hdl.handle.net/11375/23979

►

Haze and smog are among the most common environmental factors impacting image quality and, therefore, image analysis. In this paper, I propose an end-to-end generative… (more)

Subjects/Keywords: image dehazing; deep learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Liu, Z. (2018). Generic Model-Agnostic Convolutional Neural Networks for Single Image Dehazing. (Masters Thesis). McMaster University. Retrieved from http://hdl.handle.net/11375/23979

Chicago Manual of Style (16^th Edition):

Liu, Zheng. “Generic Model-Agnostic Convolutional Neural Networks for Single Image Dehazing.” 2018. Masters Thesis, McMaster University. Accessed February 27, 2020. http://hdl.handle.net/11375/23979.

MLA Handbook (7^th Edition):

Liu, Zheng. “Generic Model-Agnostic Convolutional Neural Networks for Single Image Dehazing.” 2018. Web. 27 Feb 2020.

Vancouver:

Liu Z. Generic Model-Agnostic Convolutional Neural Networks for Single Image Dehazing. [Internet] [Masters thesis]. McMaster University; 2018. [cited 2020 Feb 27]. Available from: http://hdl.handle.net/11375/23979.

Council of Science Editors:

Liu Z. Generic Model-Agnostic Convolutional Neural Networks for Single Image Dehazing. [Masters Thesis]. McMaster University; 2018. Available from: http://hdl.handle.net/11375/23979

University of Adelaide

27. Li, Teng. Deep learning for fine-grained visual recognition.

Degree: 2017, University of Adelaide

URL: http://hdl.handle.net/2440/106421

► Fine-grained object recognition is an important task in computer vision. The cross-convolutional-layer pooling method is one of the significant milestones in the development of this… (more)

▼ Fine-grained object recognition is an important task in computer vision. The cross-convolutional-layer pooling method is one of the significant milestones in the development of this field in recent years. Based on the method, we conducted a number of experiments on a new fine-grained car dataset - CompCars. The corresponding experiments illustrate its applicability and effectiveness on this newly- designed dataset. Meanwhile, based on the experiments, we found out that pooling the most distinguishable regions like car logos and headlights areas in the indicator maps, which usually have higher activations, with the local features in the same regions can achieve better results than those by pooling the whole indicator maps with the corresponding local features. Therefore, we conjecture that better performance may be achieved if we have more powerful indicator maps or pooling channels that can better highlight these distinguishable regions. Based on the above hypothesis and inspired by the cross-convolutional-layer pooling, next we propose the Spatially Weighted Pooling (SWP) method, which is a simple yet effective pooling strategy to improve fine-grained classification performance. SWP learns a dozen of pooling channels or spatial encoding masks that aggregate local convolutional feature maps with learned spatial importance information and produce more discriminative features. It can be seamlessly integrated into existing convolutional neural network (CNN) architectures such as the deep residual network. It also allows end-to-end training. SWP has few parameters to learn, usually in several hundreds, therefore does not introduce much computational overhead. SWP has shown significant capability to improve fine-grained visual recognition performance by simply adding it before fully-connected layers in off-the-shelf deep convolutional networks. We have conducted comprehensive experiments on a number of widely-used fine-grained datasets with a variety of deep CNN architectures such as Alex networks (AlexNet), VGG networks (VGGNet) and the deep residual networks (ResNet). By integrating SWP into ResNet (ResNet-SWP), we achieve state-of-the-art results on three fine-grained datasets and the MIT67 indoor scene recognition dataset. With ResNet152-SWP models, we obtain 85:2% on the bird dataset CUB-200-2011 without bounding-box annotations and 87:4% with bounding-box, 91:2% on FGVC-aircraft, 94:1% on Stanford-cars with bounding-box information and 82:5% on the MIT67 dataset. Advisors/Committee Members: Shen, Chunhua (advisor), Lin, Guosheng (advisor), School of Computer Science (school).

Subjects/Keywords: deep learning; fine-grained; recognition

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Li, T. (2017). Deep learning for fine-grained visual recognition. (Thesis). University of Adelaide. Retrieved from http://hdl.handle.net/2440/106421

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Li, Teng. “Deep learning for fine-grained visual recognition.” 2017. Thesis, University of Adelaide. Accessed February 27, 2020. http://hdl.handle.net/2440/106421.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Li, Teng. “Deep learning for fine-grained visual recognition.” 2017. Web. 27 Feb 2020.

Vancouver:

Li T. Deep learning for fine-grained visual recognition. [Internet] [Thesis]. University of Adelaide; 2017. [cited 2020 Feb 27]. Available from: http://hdl.handle.net/2440/106421.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Li T. Deep learning for fine-grained visual recognition. [Thesis]. University of Adelaide; 2017. Available from: http://hdl.handle.net/2440/106421

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

McMaster University

28. Chi, Zhixiang. IMAGE RESTORATIONS USING DEEP LEARNING TECHNIQUES.

Degree: MASc, 2018, McMaster University

URL: http://hdl.handle.net/11375/24290

►

Conventional methods for solving image restoration problems are typically built on an image degradation model and on some priors of the latent image. The model… (more)

▼

Conventional methods for solving image restoration problems are typically built on an image degradation model and on some priors of the latent image. The model of the degraded image and the prior knowledge of the latent image are necessary because the restoration is an ill posted inverse problem. However, for some applications, such as those addressed in this thesis, the image degradation process is too complex to model precisely; in addition, mathematical priors, such as low rank and sparsity of the image signal, are often too idealistic for real world images. These difficulties limit the performance of existing image restoration algorithms, but they can be, to certain extent, overcome by the techniques of machine learning, particularly deep convolutional neural networks. Machine learning allows large sample statistics far beyond what is available in a single input image to be exploited. More importantly, the big data can be used to train deep neural networks to learn the complex non-linear mapping between the degraded and original images. This circumvents the difficulty of building an explicit realistic mathematical model when the degradation causes are complex and compounded. In this thesis, we design and implement deep convolutional neural networks (DCNN) for two challenging image restoration problems: reflection removal and joint demosaicking-deblurring. The first problem is one of blind source separation; its DCNN solution requires a large set of paired clean and mixed images for training. As these paired training images are very difficult, if not impossible, to acquire in the real world, we develop a novel technique to synthesize the required training images that satisfactorily approximate the real ones. For the joint demosaicking-deblurring problem, we propose a new multiscale DCNN architecture consisting of a cascade of subnetworks so that the underlying blind deconvolution task can be broken into smaller subproblems and solved more effectively and robustly. In both cases extensive experiments are carried out. Experimental results demonstrate clear advantages of the proposed DCNN methods over existing ones.

Thesis

Master of Applied Science (MASc)

Advisors/Committee Members: Wu, Xiaolin, Electrical and Computer Engineering.

Subjects/Keywords: Image restoration; Deep learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Chi, Z. (2018). IMAGE RESTORATIONS USING DEEP LEARNING TECHNIQUES. (Masters Thesis). McMaster University. Retrieved from http://hdl.handle.net/11375/24290

Chicago Manual of Style (16^th Edition):

Chi, Zhixiang. “IMAGE RESTORATIONS USING DEEP LEARNING TECHNIQUES.” 2018. Masters Thesis, McMaster University. Accessed February 27, 2020. http://hdl.handle.net/11375/24290.

MLA Handbook (7^th Edition):

Chi, Zhixiang. “IMAGE RESTORATIONS USING DEEP LEARNING TECHNIQUES.” 2018. Web. 27 Feb 2020.

Vancouver:

Chi Z. IMAGE RESTORATIONS USING DEEP LEARNING TECHNIQUES. [Internet] [Masters thesis]. McMaster University; 2018. [cited 2020 Feb 27]. Available from: http://hdl.handle.net/11375/24290.

Council of Science Editors:

Chi Z. IMAGE RESTORATIONS USING DEEP LEARNING TECHNIQUES. [Masters Thesis]. McMaster University; 2018. Available from: http://hdl.handle.net/11375/24290

University of Waterloo

29. Tang, Yichuan. Robust Visual Recognition Using Multilayer Generative Neural Networks.

Degree: 2010, University of Waterloo

URL: http://hdl.handle.net/10012/5376

► Deep generative neural networks such as the Deep Belief Network and Deep Boltzmann Machines have been used successfully to model high dimensional visual data. However,… (more)

Subjects/Keywords: Neural Networks; Deep Learning

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

Tang, Y. (2010). Robust Visual Recognition Using Multilayer Generative Neural Networks. (Thesis). University of Waterloo. Retrieved from http://hdl.handle.net/10012/5376

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

Tang, Yichuan. “Robust Visual Recognition Using Multilayer Generative Neural Networks.” 2010. Thesis, University of Waterloo. Accessed February 27, 2020. http://hdl.handle.net/10012/5376.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

Tang, Yichuan. “Robust Visual Recognition Using Multilayer Generative Neural Networks.” 2010. Web. 27 Feb 2020.

Vancouver:

Tang Y. Robust Visual Recognition Using Multilayer Generative Neural Networks. [Internet] [Thesis]. University of Waterloo; 2010. [cited 2020 Feb 27]. Available from: http://hdl.handle.net/10012/5376.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

Tang Y. Robust Visual Recognition Using Multilayer Generative Neural Networks. [Thesis]. University of Waterloo; 2010. Available from: http://hdl.handle.net/10012/5376

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

UCLA

30. JI, NAN. Incomplete Image Filling by Popular Deep Learning Methods.

Degree: Statistics, 2019, UCLA

URL: http://www.escholarship.org/uc/item/1tz4d61x

► Incomplete image filling task, often known as the image inpainting task, is a popular topic in the applied deep learning field. This thesis paper considers… (more)

Subjects/Keywords: Statistics; Deep Learning; Image Inpainting

Record Details Similar Records Cite « Share

❌

APA · Chicago · MLA · Vancouver · CSE | Export to Zotero / EndNote / Reference Manager

APA (6^th Edition):

JI, N. (2019). Incomplete Image Filling by Popular Deep Learning Methods. (Thesis). UCLA. Retrieved from http://www.escholarship.org/uc/item/1tz4d61x

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Chicago Manual of Style (16^th Edition):

JI, NAN. “Incomplete Image Filling by Popular Deep Learning Methods.” 2019. Thesis, UCLA. Accessed February 27, 2020. http://www.escholarship.org/uc/item/1tz4d61x.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

MLA Handbook (7^th Edition):

JI, NAN. “Incomplete Image Filling by Popular Deep Learning Methods.” 2019. Web. 27 Feb 2020.

Vancouver:

JI N. Incomplete Image Filling by Popular Deep Learning Methods. [Internet] [Thesis]. UCLA; 2019. [cited 2020 Feb 27]. Available from: http://www.escholarship.org/uc/item/1tz4d61x.

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

Council of Science Editors:

JI N. Incomplete Image Filling by Popular Deep Learning Methods. [Thesis]. UCLA; 2019. Available from: http://www.escholarship.org/uc/item/1tz4d61x

Note: this citation may be lacking information needed for this citation format:
Not specified: Masters Thesis or Doctoral Dissertation

		in
And / Or
		in
And / Or
		in
And / Or
		in

Open Access Theses and Dissertations