Implementation of continuous-time dynamics on stochastic neurochip

Shunsuke Akimoto, Akiyoshi Momoi, Shigeo Sato, Koji Nakajima

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

The hardware implementation of a neural network model using stochastic logic has been able to integrate numerous neuron units on a chip. However, the limitation of applications occurred since the stochastic neurosystem could execute only discrete-time dynamics. We have contrived a neuron model with continuous-time dynamics by using stochastic calculations. In this paper, we propose the circuit design of a new neuron circuit, and show the fabricated neurochip comprising 64 neurons with experimental results. Furthermore, a new asynchronous updating method and a new activation function circuit are proposed. These improvements enhance the performance of the neurochip greatly.

Original languageEnglish
Pages (from-to)2227-2232
Number of pages6
JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
VolumeE87-A
Issue number9
Publication statusPublished - 2004 Sep

Keywords

  • Associative memories
  • Asynchronous updating
  • Continuous-time dynamics
  • Large scale integration (LSI) implementation
  • Nonmonotonic neuron
  • Stochastic logic
  • Traveling salesman problem

ASJC Scopus subject areas

  • Signal Processing
  • Computer Graphics and Computer-Aided Design
  • Electrical and Electronic Engineering
  • Applied Mathematics

Fingerprint Dive into the research topics of 'Implementation of continuous-time dynamics on stochastic neurochip'. Together they form a unique fingerprint.

  • Cite this