A wide-dynamic-range programmable synapse for impulse neural networks

Pichet Chintrakulchai; Novat Nintunze; Angus Wu; Jack Meador

doi:10.1109/ISCAS.1990.112635

A wide-dynamic-range programmable synapse for impulse neural networks

Research output: Journal Publications and Reviews › RGC 22 - Publication in policy or professional journal

Overview

3 Scopus Citations

Scopus Metrics

View graph of relations

Author(s)

Pichet Chintrakulchai
Novat Nintunze
Angus Wu
Jack Meador

Detail(s)

Original language	English
Pages (from-to)	2975-2977
Journal / Publication	Proceedings - IEEE International Symposium on Circuits and Systems
Volume	4
Publication status	Published - 1990
Externally published	Yes

Conference

Title	1990 IEEE International Symposium on Circuits and Systems Part 4 (of 4)
City	New Orleans, LA, USA
Period	1 - 3 May 1990

Link(s)

DOI	DOI https://doi.org/10.1109/ISCAS.1990.112635 Final Published version
	Check@CityULib
Link to Scopus	https://www.scopus.com/record/display.uri?eid=2-s2.0-0025692425&origin=recordpage
Permanent Link	https://scholars.cityu.edu.hk/en/publications/publication(1805b8f1-06a7-4698-bf2b-419f51fa5209).html

Abstract

A fully-analog synapse circuit for impulse neural networks is described. The circuit is programmable over a dynamic range of several orders of magnitude. It is essentially a programmable switched-circuit source which incrementally contributes to the excitation of an impulse neuron. Shared-floating-gate FETs are used to implement a programmable current mirror exhibiting a nonvolatile storage characteristic. The synapse connection strength is modulated by incrementally adding or removing charge on the shared floating gate. A wide dynamic range is achieved through biasing the circuit to operate in the subthreshold region.