An associative memory for the on-line recognition and prediction of temporal sequences

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

Abstract

This paper presents the design of an associative memory with feedback that is capable of on-line temporal sequence learning. A framework for on-line sequence learning has been proposed, and different sequence learning models have been analysed according to this framework. The network model is an associative memory with a separate store for the sequence context of a symbol. A sparse distributed memory is used to gain scalability. The context store combines the functionality of a neural layer with a shift register. The sensitivity of the machine to the sequence context is controllable, resulting in different characteristic behaviours. The model can store and predict online sequences of various types and length. Numerical simulations on the model have been carried out to determine its properties. © 2005 IEEE.
Original languageEnglish
Title of host publicationProceedings of the International Joint Conference on Neural Networks (IJCNN) 2005 : July 31 - August 4, 2005, Hilton Montréal Bonaventure Hotel, Montréal, Québec, Canada
PublisherIEEE
Pages1223-1228
Number of pages5
Volume2
ISBN (Print)0-7803-9048-2
DOIs
Publication statusPublished - 2005

Fingerprint

Dive into the research topics of 'An associative memory for the on-line recognition and prediction of temporal sequences'. Together they form a unique fingerprint.

Cite this