Title:
ニューラルネットワークシステム、学習方法およびプログラム
Document Type and Number:
Japanese Patent JP7336710
Kind Code:
B2
Abstract:
A neural network device includes: a neuron model unit configured as a non-leaky integrate-and-fire spiking neuron and a spiking neuron with which a postsynaptic current is represented using a step function, the neuron model unit being fired once at most in one process of a neural network to indicate an output of the neural model unit itself at firing timing; and a transfer processing unit that transfers information between the neuron model unit.
More Like This:
Inventors:
Yuusuke Sakemi
Yoshio Morino
Kazuyuki Aihara
Yoshio Morino
Kazuyuki Aihara
Application Number:
JP2021507387A
Publication Date:
September 01, 2023
Filing Date:
March 18, 2020
Export Citation:
Assignee:
NEC
National University Corporation The University of Tokyo
National University Corporation The University of Tokyo
International Classes:
G06N3/08; G06N3/049
Other References:
MOSTAFA, H,"Supervised Learning Based on Temporal Coding in Spiking Neural Networks",IEEE Transactions on Neural Networks and Learning Systems [online],IEEE,2017年,Vol. 29, No. 7,pp. 3227-3235,[retrieved on 2022.08.04], Retrieved from the Internet: ,
Attorney, Agent or Firm:
Sumio Tanai
Ryuichiro Mori
Yasushi Matsunuma
Eisuke Ito
Ryuichiro Mori
Yasushi Matsunuma
Eisuke Ito