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

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

2006-11-05

arxiv.org/abs/cs/0611020v1

Computer Science

Neural and Evolutionary Computing

Published in IJCNN 2005, Montreal, Canada

Scientific paper

10.1109/IJCNN.2005.1556028

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.

Affiliated with

Also associated with

No associations

Rating

An associative memory for the on-line recognition and prediction of temporal sequences does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with An associative memory for the on-line recognition and prediction of temporal sequences, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and An associative memory for the on-line recognition and prediction of temporal sequences will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-594869