Title:
再帰型ニューラルネットワークアーキテクチャの生成のためのドメイン固有言語
Document Type and Number:
Japanese Patent JP7169091
Kind Code:
B2
Abstract:
A system automatically generates recurrent neural network (RNN) architectures for performing specific tasks, for example, machine translation. The system represents RNN architectures using a domain specific language (DSL). The system generates candidate RNN architectures. The system predicts performances of the generated candidate RNN architectures, for example, using a neural network. The system filters the candidate RNN architectures based on their predicted performance. The system generates code for selected a candidate architectures. The generated code represents an RNN that is configured to perform the specific task. The system executes the generated code, for example, to evaluate an RNN or to use the RNN in an application.
Inventors:
Stephen Joseph Merity
Richard Socher
james bradbury
Kaiming Shon
Richard Socher
james bradbury
Kaiming Shon
Application Number:
JP2018095206A
Publication Date:
November 10, 2022
Filing Date:
May 17, 2018
Export Citation:
Assignee:
Salesforce.com Incorporated
International Classes:
G06N3/08; G06N3/04
Domestic Patent References:
| JP2004192584A |
Other References:
ZOPH, Barret, et al.,Neural Architecture Search with Reinforcement Learning,arXiv.org,2017年02月15日,[検索日:2022.05.10]
Attorney, Agent or Firm:
Tadashige Ito
Tadahiko Ito
Shinsuke Onuki
Tadahiko Ito
Shinsuke Onuki