Storing temporal sequences of patterns in neural networks

Dilip Krishnaswamy; Kishan Mehrotra; Chilukuri K. Mohan; Sanjay Ranka

doi:10.1117/12.162028

Storing temporal sequences of patterns in neural networks

Dilip Krishnaswamy, Kishan Mehrotra, Chilukuri K. Mohan, Sanjay Ranka

Department of Electrical Engineering & Computer Science

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

Abstract

This paper presents neural network models for storing terminating and cyclic temporal sequences of patterns under synchronous, sequential and asynchronous dynamics. We use fully interconnected neural networks, with asymmetric weight connections for synchronous and sequential dynamics and a layered neural network with feedback for asynchronous dynamics. The networks were successfully implemented and the number of patterns that could be stored and recalled was approximately 12 percent of the size of the patterns in the network.

Original language	English (US)
Pages (from-to)	120-126
Number of pages	7
Journal	Proceedings of SPIE - The International Society for Optical Engineering
Volume	2032
DOIs	https://doi.org/10.1117/12.162028
State	Published - Oct 29 1993
Event	Neural and Stochastic Methods in Image and Signal Processing II 1993 - San Diego, United States Duration: Jul 11 1993 → Jul 16 1993

ASJC Scopus subject areas

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

Access to Document

10.1117/12.162028

Cite this

@article{bfc6ddeda0884469ac9d9d8dfd967867,

title = "Storing temporal sequences of patterns in neural networks",

abstract = "This paper presents neural network models for storing terminating and cyclic temporal sequences of patterns under synchronous, sequential and asynchronous dynamics. We use fully interconnected neural networks, with asymmetric weight connections for synchronous and sequential dynamics and a layered neural network with feedback for asynchronous dynamics. The networks were successfully implemented and the number of patterns that could be stored and recalled was approximately 12 percent of the size of the patterns in the network.",

author = "Dilip Krishnaswamy and Kishan Mehrotra and Mohan, {Chilukuri K.} and Sanjay Ranka",

year = "1993",

month = oct,

day = "29",

doi = "10.1117/12.162028",

language = "English (US)",

volume = "2032",

pages = "120--126",

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

issn = "0277-786X",

publisher = "SPIE",

}

TY - JOUR

T1 - Storing temporal sequences of patterns in neural networks

AU - Krishnaswamy, Dilip

AU - Mehrotra, Kishan

AU - Mohan, Chilukuri K.

AU - Ranka, Sanjay

PY - 1993/10/29

Y1 - 1993/10/29

N2 - This paper presents neural network models for storing terminating and cyclic temporal sequences of patterns under synchronous, sequential and asynchronous dynamics. We use fully interconnected neural networks, with asymmetric weight connections for synchronous and sequential dynamics and a layered neural network with feedback for asynchronous dynamics. The networks were successfully implemented and the number of patterns that could be stored and recalled was approximately 12 percent of the size of the patterns in the network.

AB - This paper presents neural network models for storing terminating and cyclic temporal sequences of patterns under synchronous, sequential and asynchronous dynamics. We use fully interconnected neural networks, with asymmetric weight connections for synchronous and sequential dynamics and a layered neural network with feedback for asynchronous dynamics. The networks were successfully implemented and the number of patterns that could be stored and recalled was approximately 12 percent of the size of the patterns in the network.

UR - http://www.scopus.com/inward/record.url?scp=85076121397&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85076121397&partnerID=8YFLogxK

U2 - 10.1117/12.162028

DO - 10.1117/12.162028

M3 - Conference Article

AN - SCOPUS:85076121397

SN - 0277-786X

VL - 2032

SP - 120

EP - 126

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

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

T2 - Neural and Stochastic Methods in Image and Signal Processing II 1993

Y2 - 11 July 1993 through 16 July 1993

ER -

Storing temporal sequences of patterns in neural networks

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this