Title:
ニューラルネットワークのアナログハードウェア実現
Document Type and Number:
Japanese Patent JP7371235
Kind Code:
B2
Abstract:
Systems and methods are provided for analog hardware realization of neural networks. The method incudes obtaining a neural network topology and weights of a trained neural network. The method also includes transforming the neural network topology to an equivalent analog network of analog components. The method also includes computing a weight matrix for the equivalent analog network based on the weights of the trained neural network. Each element of the weight matrix represents a respective connection between analog components of the equivalent analog network. The method also includes generating a schematic model for implementing the equivalent analog network based on the weight matrix, including selecting component values for the analog components.
Inventors:
Timofe Jeffs, Alexanders
Maslov, Boris
Godowsky, Dmitry Yuryevich
Kovshov, Nikolai Vadimovich
Maslov, Boris
Godowsky, Dmitry Yuryevich
Kovshov, Nikolai Vadimovich
Application Number:
JP2022515539A
Publication Date:
October 30, 2023
Filing Date:
June 25, 2020
Export Citation:
Assignee:
Poring Technology Limited
International Classes:
G06N3/063; G06G7/60
Domestic Patent References:
| JP2178758A | ||||
| JP2019003546A |
Foreign References:
| US20080154822 |
Attorney, Agent or Firm:
Yoshiyuki Inaba
Toshifumi Onuki
Akihiko Eguchi
Kazuhiko Naito
Toshifumi Onuki
Akihiko Eguchi
Kazuhiko Naito
Previous Patent: Quantum gate optimization method, device, equipment, storage medium and computer program
Next Patent: How to prepare SSZ-26/33 zeolite
Next Patent: How to prepare SSZ-26/33 zeolite