Exploring Neural Architecture Search Space via Deep Deterministic Sampling

Exploring Neural Architecture Search Space via Deep Deterministic Sampling

Recent developments in Neural Architecture Search (NAS) resort to training the supernet of a predefined search space with weight sharing to speed up architecture evaluation. These include random search schemes, as well as various schemes based on optimization or reinforcement learning, in particular...

Full description

Bibliographic Details
Main Authors: Keith G. Mills, Mohammad Salameh, Di Niu, Fred X. Han, Seyed Saeed Changiz Rezaei, Hengshuai Yao, Wei Lu, Shuo Lian, Shangling Jui
Format: Article
Language:English
Published: IEEE 2021-01-01
Series:IEEE Access
Subjects:
Neural architecture search
reinforcement learning
differentiable optimization
Online Access:https://ieeexplore.ieee.org/document/9503404/

Internet

https://ieeexplore.ieee.org/document/9503404/

Similar Items