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

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.

• Type: Journal
• Year: 2006
• Where: CORR
• Authors: Joy Bose, Stephen B. Furber, Jonathan L. Shapiro
• Keywords: Associative Memory, CORR 2006, Education, On-line Sequences, Sequence Context