Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
METHOD OF NEURAL ARCHITECTURE SEARCH USING CONTINUOUS ACTION REINFORCEMENT LEARNING
Document Type and Number:
WIPO Patent Application WO/2022/068934
Kind Code:
A1
Abstract:
A method and system for generating neural architectures to perform a particular task. An actor neural network, as part of a continuous action reinforcement learning (RL) agent, generates a randomized continuous actions parameters to encourage exploration of a search space to generate candidate architectures without bias. The continuous action parameters are discretized and applied to a search space to generate candidate architectures, the performance of which for performing the particular task is evaluated. Corresponding reward and state are determined based on the performance. A critic neural network, as part of the continuous action RL agent, learns a mapping of the continuous action to a reward using modified Deep Deterministic Policy Gradient (DDPG) with quantile loss function by sampling a list of top performing architectures. The actor neural network is updated with the learned mapping.

More Like This:
WO/2020/204744HIERARCHICAL SEQUENCE MEMORY
WO/1997/036248METHOD FOR DETERMINATION OF WEIGHTS, SUITABLE FOR ELIMINATION, OF A NEURAL NETWORK USING A COMPUTER
WO/2022/132419AUGMENTED TRAINING DATA FOR END-TO-END MODELS
Inventors:
SALAMEH MOHAMMAD (CA)
MILLS KEITH GEORGE (CA)
NIU DI (CA)
Application Number:
PCT/CN2021/122384
Publication Date:
April 07, 2022
Filing Date:
September 30, 2021
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
HUAWEI TECH CO LTD (CN)
International Classes:
G06N3/08
Domestic Patent References:
WO2020160252A12020-08-06
WO2019007388A12019-01-10
Foreign References:
CN110651279A2020-01-03
US20200082275A12020-03-12
US20200293883A12020-09-17
Download PDF:
View/Download PDF      PDF Help



 
Previous Patent: COMPOUNDS AND METHODS OF TREATING DISEASES

Next Patent: ELEVATOR RESOURCE SCHEDULING METHOD AND APPARATUS