Title:
ニューラルアーキテクチャ検索
Document Type and Number:
Japanese Patent JP7439151
Kind Code:
B2
Abstract:
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining neural network architectures. One of the methods includes generating, using a controller neural network, a batch of output sequences, each output sequence in the batch specifying a respective subset of a plurality of components of a large neural network that should be active during the processing of inputs by the large neural network; for each output sequence in the batch: determining a performance metric of the large neural network on the particular neural network task (i) in accordance with current values of the large network parameters and (ii) with only the subset of components specified by the output sequences active; and using the performance metrics for the output sequences in the batch to adjust the current values of the controller parameters of the controller neural network.
Inventors:
Barrett Zoff
Yun Ja Guan
Hu hi fam
Quark Vie
Yun Ja Guan
Hu hi fam
Quark Vie
Application Number:
JP2022041344A
Publication Date:
February 27, 2024
Filing Date:
March 16, 2022
Export Citation:
Assignee:
Google LLC
International Classes:
G06N3/082; G06N3/044; G06N3/0464; G06N3/092
Domestic Patent References:
| JP2017004509A |
Other References:
ZOPH, B et al.,“Neural Architecture Search with Reinforcement Learning”,arXiv.org [online],2017年,pp. 1-16,[retrieved on 2023.04.17], Retrieved from the Internet: ,
Attorney, Agent or Firm:
Yasuhiko Murayama
Shinya Mihiro
Tatsuhiko Abe
Shinya Mihiro
Tatsuhiko Abe