You searched for +publisher:"Delft University of Technology" +contributor:("Zhou, Hongpeng").
Showing records 1 – 4 of
4 total matches.
No search limiters apply to these results.
Delft University of Technology
1.
Li, Mingxi (author).
Efficient Neural Architecture Search for Language Modeling.
Degree: 2019, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:aa5c948d-43c4-480d-9818-43949c67a3b5 
► Neural networks have achieved great success in many difficult learning tasks like image classification, speech recognition and natural language processing. However, neural architectures are hard…
(more)
▼ Neural networks have achieved great success in many difficult learning tasks like image classification, speech recognition and natural language processing. However, neural architectures are hard to design, which requires lots of knowledge and time of human experts. Therefore, there has been a growing interest in automating the process of designing neural architectures. Though these searched architectures have achieved competitive performance on various tasks, the efficiency of NAS still needs to be improved. Moreover, current neural architecture search approach disregards the dependency between a node and its predecessors and successors. This thesis builds upon BayesNAS which employs the classic Bayesian learning method to search for CNN architectures, and extends it to the problem of neural architecture search for recurrent architectures. Hierarchical sparse priors are used to model the architecture parameters to alleviate the dependency issue. Since the update of posterior variance is based on Laplace approximation, an efficient method to compute the Hessian of recurrent layer is proposed. We can find candidated architectures after training the over-parameterized network for only one epoch. Our experiments on Penn Treebank and WikiText-2 show that competitive architectures can be found in 0.3 GPU days using a single GPU for language modeling task. We find that our algorithm is more efficient than state-of-the-art.
Electrical Engineer | Embedded Systems
Advisors/Committee Members: Oliehoek, Frans (mentor), Pan, Wei (graduation committee), van Gemert, Jan (graduation committee), Zhou, Hongpeng (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: NAS; Deep learning; 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):
Li, M. (. (2019). Efficient Neural Architecture Search for Language Modeling. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:aa5c948d-43c4-480d-9818-43949c67a3b5
Chicago Manual of Style (16th Edition):
Li, Mingxi (author). “Efficient Neural Architecture Search for Language Modeling.” 2019. Masters Thesis, Delft University of Technology. Accessed March 02, 2021.
http://resolver.tudelft.nl/uuid:aa5c948d-43c4-480d-9818-43949c67a3b5.
MLA Handbook (7th Edition):
Li, Mingxi (author). “Efficient Neural Architecture Search for Language Modeling.” 2019. Web. 02 Mar 2021.
Vancouver:
Li M(. Efficient Neural Architecture Search for Language Modeling. [Internet] [Masters thesis]. Delft University of Technology; 2019. [cited 2021 Mar 02].
Available from: http://resolver.tudelft.nl/uuid:aa5c948d-43c4-480d-9818-43949c67a3b5.
Council of Science Editors:
Li M(. Efficient Neural Architecture Search for Language Modeling. [Masters Thesis]. Delft University of Technology; 2019. Available from: http://resolver.tudelft.nl/uuid:aa5c948d-43c4-480d-9818-43949c67a3b5
Delft University of Technology
2.
Tian, Yuan (author).
Model Free Reinforcement Learning with Stability Guarantee.
Degree: 2019, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:dde4e58f-e109-4e7f-8ecb-ed1734294e5c
► Model-free reinforcement learning has proved to be successful in many tasks such as robotic manipulator, video games, and even stock trading. However, as the dynamics…
(more)
▼ Model-free reinforcement learning has proved to be successful in many tasks such as robotic manipulator, video games, and even stock trading. However, as the dynamics of the environment is unmodelled, it is fundamentally difficult to ensure the learned policy to be absolutely reliable and its performance is guaranteed. In this thesis, we borrow the concept of stability and Lyapunov analysis in control theory to design a policy with stability guarantee and assure the guaranteed behaviors of the agent. A novel sample-based approach is proposed for analyzing the stability of a learning control system, and on the basis of the theoretical result, we establish a practical model-free learning framework with provable stability, safety and performance guarantees. % Specifically, a novel locally constrained method is proposed to solve the safety constrained problems with lower conservatism. In our solution, a Lyapunov function is searched automatically to guarantee the closed-loop system stability, which also guides the simultaneous learning (covering both the policy and value-based learning methods). Our approach is evaluated on a series of discrete and continuous control benchmarks and largely outperforms the state-of-the-art results concerning unconstrained and constrained problems. It is also shown that the algorithm has the ability of recovery to equilibrium under perturbation using the policy with stability guarantee. (Anonymous code is available to reproduce the experimental esults\footnote{\url{https://github.com/RLControlTheoreticGuarantee/GuaranteeLearningControl}}.) Since sometimes the constraint is hard to define, we introduce a novel method to learn a constraint by representing the bad cases or situations as a distribution, and the constraint is the Wasserstein distance between the distribution.
Mechanical Engineering | Vehicle Engineering
Advisors/Committee Members: Pan, Wei (mentor), Zhou, Hongpeng (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: Reinforcement 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):
Tian, Y. (. (2019). Model Free Reinforcement Learning with Stability Guarantee. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:dde4e58f-e109-4e7f-8ecb-ed1734294e5c
Chicago Manual of Style (16th Edition):
Tian, Yuan (author). “Model Free Reinforcement Learning with Stability Guarantee.” 2019. Masters Thesis, Delft University of Technology. Accessed March 02, 2021.
http://resolver.tudelft.nl/uuid:dde4e58f-e109-4e7f-8ecb-ed1734294e5c.
MLA Handbook (7th Edition):
Tian, Yuan (author). “Model Free Reinforcement Learning with Stability Guarantee.” 2019. Web. 02 Mar 2021.
Vancouver:
Tian Y(. Model Free Reinforcement Learning with Stability Guarantee. [Internet] [Masters thesis]. Delft University of Technology; 2019. [cited 2021 Mar 02].
Available from: http://resolver.tudelft.nl/uuid:dde4e58f-e109-4e7f-8ecb-ed1734294e5c.
Council of Science Editors:
Tian Y(. Model Free Reinforcement Learning with Stability Guarantee. [Masters Thesis]. Delft University of Technology; 2019. Available from: http://resolver.tudelft.nl/uuid:dde4e58f-e109-4e7f-8ecb-ed1734294e5c
Delft University of Technology
3.
Vroom, Quinn (author).
POMDP based online parameter estimation for autonomous passenger vehicles: Researching online tyre parameter estimation performance by improving the trajectory using a POMDP algorithm.
Degree: 2019, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:192fdf22-0c21-49f4-9413-211276871008
► The internal model is an important piece of the control system of an autonomous driving vehicle. In order for the model to deliver accurate predictions,…
(more)
▼ The internal model is an important piece of the control system of an autonomous driving vehicle. In order for the model to deliver accurate predictions, a valid model structure and well chosen parameters are needed. Model parameters can be highly fluctuating or complex to predict, especially when looking into tyre ground surface interaction models. Instead of predicting parameter values beforehand, they could be estimated and updated in real-time. Fluctuation or incorrectness can be adjusted while driving. However, this uncertainty in parameter value must be accounted for when applying control. Solving this problem by regarding the uncertainty in parameters of the internal vehicle model as a POMDP has been researched in this paper. The research question being: is it worthwhile to use the POMDP approach for online parameter estimation of autonomous passenger vehicles? To answer this multiple sub-questions have been composed. We start off looking into: what is the most suitable vehicle model? Different vehicle models and tyre models were compared. Literature showed the bicycle model in combination with the linearized tyre model to be most suitable for autonomous passenger vehicles. The next question is: What is the most promising algorithm? Using literature, suitable algorithms for solving this POMDP have been found and compared. From three compelling algorithms, the one best fitting the autonomous driving criteria was chosen. Knowing the model and the algorithm for the simulation the next question became: Does the algorithm perform on a vehicle model? To answer this question, the simulation has been implemented in MATLAB and performance has been tested. The results showed significant increase in parameter estimation performance. Within 2 timesteps the estimate had converged correctly. The next question is: Does the algorithm perform within realistic bounds? To answer this question, the same simulation as before has been used, but now with saturation on the steering input. This showed parameter estimation performance increase compared to the original trajectory, but not as overwhelming as without saturation. The next question is: Does the algorithm suffer from high noise? To answer this question, the same simulation has been used, but now with different levels of noise. The results showed parameter estimation performance significantly affected by increasing noise. The final sub-question is: Does the algorithm suit increasing model complexity? To answer this question, the amount of parameters have been increased in the simulation and there has been looked into the large matrices that accompany the algorithm. Results showed that increasing the complexity has a significant effect on the size of the simulation and algorithm matrices. In conclusion, from all of these experiments arose some very interesting results. This produced a useful insight into the strengths and weaknesses of the POMDP algorithm performing on a passenger vehicle, answering the research question. This also led to various recommendations for future…
Advisors/Committee Members: Wisse, Martijn (mentor), Spaan, Matthijs (graduation committee), Zhou, Hongpeng (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: POMDP; parameter estimation; online; tyre 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):
Vroom, Q. (. (2019). POMDP based online parameter estimation for autonomous passenger vehicles: Researching online tyre parameter estimation performance by improving the trajectory using a POMDP algorithm. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:192fdf22-0c21-49f4-9413-211276871008
Chicago Manual of Style (16th Edition):
Vroom, Quinn (author). “POMDP based online parameter estimation for autonomous passenger vehicles: Researching online tyre parameter estimation performance by improving the trajectory using a POMDP algorithm.” 2019. Masters Thesis, Delft University of Technology. Accessed March 02, 2021.
http://resolver.tudelft.nl/uuid:192fdf22-0c21-49f4-9413-211276871008.
MLA Handbook (7th Edition):
Vroom, Quinn (author). “POMDP based online parameter estimation for autonomous passenger vehicles: Researching online tyre parameter estimation performance by improving the trajectory using a POMDP algorithm.” 2019. Web. 02 Mar 2021.
Vancouver:
Vroom Q(. POMDP based online parameter estimation for autonomous passenger vehicles: Researching online tyre parameter estimation performance by improving the trajectory using a POMDP algorithm. [Internet] [Masters thesis]. Delft University of Technology; 2019. [cited 2021 Mar 02].
Available from: http://resolver.tudelft.nl/uuid:192fdf22-0c21-49f4-9413-211276871008.
Council of Science Editors:
Vroom Q(. POMDP based online parameter estimation for autonomous passenger vehicles: Researching online tyre parameter estimation performance by improving the trajectory using a POMDP algorithm. [Masters Thesis]. Delft University of Technology; 2019. Available from: http://resolver.tudelft.nl/uuid:192fdf22-0c21-49f4-9413-211276871008
Delft University of Technology
4.
YANG, MINGHAO (author).
Efficient Neural Network Architecture Search.
Degree: 2019, Delft University of Technology
URL: http://resolver.tudelft.nl/uuid:9985c543-cb4e-4259-b6f8-b44ba433f1e3
► One-Shot Neural Architecture Search (NAS) is a promising method to significantly reduce search time without any separate training. It can be treated as a Network…
(more)
▼ One-Shot Neural Architecture Search (NAS) is a promising method to significantly reduce search time without any separate training. It can be treated as a Network Compression problem on the architecture parameters from an overparameterized network. However, there are two issues associated with most one-shot NAS methods. First, dependencies between a node and its predecessors and successors are often disregarded which result in improper treatment over zero operations. Second, architecture parameters pruning based on their magnitude is questionable. In this thesis, classic Bayesian learning approach is applied to alleviate these two issues. Unlike other NAS methods, we train the over-parameterized network for only one epoch before update network architecture. Impressively, this enabled us to find the optimal architecture in both proxy and proxyless tasks on CIFAR-10 within only 0.2 GPU days using a single GPU. As a byproduct, our approach can be transferred directly to convolutional neural networks compression by enforcing structural sparsity that is able to achieve extremely sparse networks without accuracy deterioration.
Mechanical Engineering | Vehicle Engineering
Advisors/Committee Members: Pan, Wei (mentor), Zhou, Hongpeng (mentor), Gavrila, Dariu (graduation committee), van de Plas, Raf (graduation committee), Delft University of Technology (degree granting institution).
Subjects/Keywords: NAS; Deep Learning; ICML; 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):
YANG, M. (. (2019). Efficient Neural Network Architecture Search. (Masters Thesis). Delft University of Technology. Retrieved from http://resolver.tudelft.nl/uuid:9985c543-cb4e-4259-b6f8-b44ba433f1e3
Chicago Manual of Style (16th Edition):
YANG, MINGHAO (author). “Efficient Neural Network Architecture Search.” 2019. Masters Thesis, Delft University of Technology. Accessed March 02, 2021.
http://resolver.tudelft.nl/uuid:9985c543-cb4e-4259-b6f8-b44ba433f1e3.
MLA Handbook (7th Edition):
YANG, MINGHAO (author). “Efficient Neural Network Architecture Search.” 2019. Web. 02 Mar 2021.
Vancouver:
YANG M(. Efficient Neural Network Architecture Search. [Internet] [Masters thesis]. Delft University of Technology; 2019. [cited 2021 Mar 02].
Available from: http://resolver.tudelft.nl/uuid:9985c543-cb4e-4259-b6f8-b44ba433f1e3.
Council of Science Editors:
YANG M(. Efficient Neural Network Architecture Search. [Masters Thesis]. Delft University of Technology; 2019. Available from: http://resolver.tudelft.nl/uuid:9985c543-cb4e-4259-b6f8-b44ba433f1e3
. 
Open Access Theses and Dissertations