A localized learning rule for analog VLSI implementation of neural networks

Hiroyuki Wasaki; Yoshihiko Horio; Shogo Nakamura

A localized learning rule for analog VLSI implementation of neural networks

Hiroyuki Wasaki, Yoshihiko Horio, Shogo Nakamura

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

A modified Hebbian type learning rule for self-organization which uses only the local information is proposed. As the result of computer simulations of self-organizing networks, the validity of the rule was confirmed and learning speed was improved. Furthermore, circuit examples for implementing the learning rule are proposed.

Original language	English
Title of host publication	Midwest Symposium on Circuits and Systems
Publisher	Publ by IEEE
Pages	17-20
Number of pages	4
ISBN (Print)	0780300815
Publication status	Published - 1991 Dec 1
Externally published	Yes
Event	33rd Midwest Symposium on Circuits and Systems - Calgary, Alberta, Can Duration: 1990 Aug 12 → 1990 Aug 15

Publication series

Name	Midwest Symposium on Circuits and Systems
Volume	1

Other

Other	33rd Midwest Symposium on Circuits and Systems
City	Calgary, Alberta, Can
Period	90/8/12 → 90/8/15

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'A localized learning rule for analog VLSI implementation of neural networks'. Together they form a unique fingerprint.

Cite this

@inproceedings{ab14ed7c39c841d9ad1c2710e89e2b2a,

title = "A localized learning rule for analog VLSI implementation of neural networks",

abstract = "A modified Hebbian type learning rule for self-organization which uses only the local information is proposed. As the result of computer simulations of self-organizing networks, the validity of the rule was confirmed and learning speed was improved. Furthermore, circuit examples for implementing the learning rule are proposed.",

author = "Hiroyuki Wasaki and Yoshihiko Horio and Shogo Nakamura",

year = "1991",

month = dec,

day = "1",

language = "English",

isbn = "0780300815",

series = "Midwest Symposium on Circuits and Systems",

publisher = "Publ by IEEE",

pages = "17--20",

booktitle = "Midwest Symposium on Circuits and Systems",

note = "33rd Midwest Symposium on Circuits and Systems ; Conference date: 12-08-1990 Through 15-08-1990",

}

TY - GEN

T1 - A localized learning rule for analog VLSI implementation of neural networks

AU - Wasaki, Hiroyuki

AU - Horio, Yoshihiko

AU - Nakamura, Shogo

PY - 1991/12/1

Y1 - 1991/12/1

N2 - A modified Hebbian type learning rule for self-organization which uses only the local information is proposed. As the result of computer simulations of self-organizing networks, the validity of the rule was confirmed and learning speed was improved. Furthermore, circuit examples for implementing the learning rule are proposed.

AB - A modified Hebbian type learning rule for self-organization which uses only the local information is proposed. As the result of computer simulations of self-organizing networks, the validity of the rule was confirmed and learning speed was improved. Furthermore, circuit examples for implementing the learning rule are proposed.

UR - http://www.scopus.com/inward/record.url?scp=0026385064&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026385064&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0026385064

SN - 0780300815

T3 - Midwest Symposium on Circuits and Systems

SP - 17

EP - 20

BT - Midwest Symposium on Circuits and Systems

PB - Publ by IEEE

T2 - 33rd Midwest Symposium on Circuits and Systems

Y2 - 12 August 1990 through 15 August 1990

ER -