Advanced search options
You searched for
subject:(ICML). One record found.
▼ Search Limiters
Delft University of Technology
1. YANG, MINGHAO (author). Efficient Neural Network Architecture Search.
Degree: 2019, Delft University of Technology
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 EngineeringAdvisors/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).
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 January 19, 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. 19 Jan 2021.
YANG M(. Efficient Neural Network Architecture Search. [Internet] [Masters thesis]. Delft University of Technology; 2019. [cited 2021 Jan 19]. 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