Title:
ニューラル記号コンピューティング
Document Type and Number:
Japanese Patent JP7391212
Kind Code:
B2
Abstract:
A neural-symbolic computing engine can have two or more modules that are configured to cooperate with each other in order to create one or more gradient-based machine learning models that use machine learning on i) knowledge representations and ii) reasoning to solve an issue. A model representation module in the neural-symbolic computing engine is configured to apply one or more mathematical functions, at least including a logit transform, to truth values from first order logic elements supplied from a language module of the neural-symbolic computing engine.
Inventors:
Burns, John
Lower, Richard
silverfarb, andrew
Lower, Richard
silverfarb, andrew
Application Number:
JP2022529036A
Publication Date:
December 04, 2023
Filing Date:
March 15, 2021
Export Citation:
Assignee:
SRI International
International Classes:
G06N3/042; G06N3/084
Domestic Patent References:
| JP2018041445A |
Foreign References:
| US20070239632 | ||||
| US20120158685 |
Other References:
SIKKA, Karan et al.,Deep Adaptive Semantic Logic (DASL): Compiling Declarative Knowledge into Deep Neural Networks,arXiv [online],2020年03月16日,https://arxiv.org/abs/2003.07344v1 [2023年4月4日検索]
Attorney, Agent or Firm:
Shinichi Iizuka
Ken Iizuka
Ken Iizuka