Modified MAXNET with fast convergence net

Orly Yadid-Pecht; Moshe Gur

doi:10.1117/12.169957

Modified MAXNET with fast convergence net

Orly Yadid-Pecht, Moshe Gur

Research output: Contribution to journal › Conference article › peer-review

Abstract

A biologically-inspired modification to MAXNET is proposed. Unlike the original net where the weights are constant, the weights in the new net are dynamically changed. Consequently, the modified net achieves a drastic improvement in convergence rate. A simple hardware implementation for the modified net is presented.

Original language	English
Pages (from-to)	111-118
Number of pages	8
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	2243
DOIs	https://doi.org/10.1117/12.169957
State	Published - 2 Mar 1994
Externally published	Yes
Event	Applications of Artificial Neural Networks V 1994 - Orlando, United States Duration: 4 Apr 1994 → 8 Apr 1994

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Condensed Matter Physics
Computer Science Applications
Applied Mathematics
Electrical and Electronic Engineering

Access to Document

10.1117/12.169957

Cite this

@article{0b56cac431f1477a981205543b1d451b,

title = "Modified MAXNET with fast convergence net",

abstract = "A biologically-inspired modification to MAXNET is proposed. Unlike the original net where the weights are constant, the weights in the new net are dynamically changed. Consequently, the modified net achieves a drastic improvement in convergence rate. A simple hardware implementation for the modified net is presented.",

author = "Orly Yadid-Pecht and Moshe Gur",

year = "1994",

month = mar,

day = "2",

doi = "10.1117/12.169957",

language = "English",

volume = "2243",

pages = "111--118",

journal = "Proceedings of SPIE - The International Society for Optical Engineering",

issn = "0277-786X",

publisher = "SPIE",

}

TY - JOUR

T1 - Modified MAXNET with fast convergence net

AU - Yadid-Pecht, Orly

AU - Gur, Moshe

PY - 1994/3/2

Y1 - 1994/3/2

N2 - A biologically-inspired modification to MAXNET is proposed. Unlike the original net where the weights are constant, the weights in the new net are dynamically changed. Consequently, the modified net achieves a drastic improvement in convergence rate. A simple hardware implementation for the modified net is presented.

AB - A biologically-inspired modification to MAXNET is proposed. Unlike the original net where the weights are constant, the weights in the new net are dynamically changed. Consequently, the modified net achieves a drastic improvement in convergence rate. A simple hardware implementation for the modified net is presented.

UR - http://www.scopus.com/inward/record.url?scp=85076814197&partnerID=8YFLogxK

U2 - 10.1117/12.169957

DO - 10.1117/12.169957

M3 - Conference article

AN - SCOPUS:85076814197

VL - 2243

SP - 111

EP - 118

JO - Proceedings of SPIE - The International Society for Optical Engineering

JF - Proceedings of SPIE - The International Society for Optical Engineering

SN - 0277-786X

T2 - Applications of Artificial Neural Networks V 1994

Y2 - 4 April 1994 through 8 April 1994

ER -

Modified MAXNET with fast convergence net

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this