English

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

Neural and Evolutionary Computing 2007-05-23 v1 Artificial Intelligence

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 on-line sequences of various types and length. Numerical simulations on the model have been carried out to determine its properties.

Keywords

Cite

@article{arxiv.cs/0611020,
  title  = {An associative memory for the on-line recognition and prediction of temporal sequences},
  author = {J. Bose and S. B. Furber and J. L. Shapiro},
  journal= {arXiv preprint arXiv:cs/0611020},
  year   = {2007}
}

Comments

Published in IJCNN 2005, Montreal, Canada