Storing temporal sequences of patterns in neural networks

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

Research output: Contribution to journalConference articlepeer-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 languageEnglish (US)
Pages (from-to)120-126
Number of pages7
JournalProceedings of SPIE - The International Society for Optical Engineering
Volume2032
DOIs
StatePublished - Oct 29 1993
EventNeural and Stochastic Methods in Image and Signal Processing II 1993 - San Diego, United States
Duration: Jul 11 1993Jul 16 1993

ASJC Scopus subject areas

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

Fingerprint Dive into the research topics of 'Storing temporal sequences of patterns in neural networks'. Together they form a unique fingerprint.

Cite this