An associative memory for the on-line recognition and prediction of temporal sequences
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.
- Publication:
-
arXiv e-prints
- Pub Date:
- November 2006
- DOI:
- 10.48550/arXiv.cs/0611020
- arXiv:
- arXiv:cs/0611020
- Bibcode:
- 2006cs.......11020B
- Keywords:
-
- Computer Science - Neural and Evolutionary Computing;
- Computer Science - Artificial Intelligence
- E-Print:
- Published in IJCNN 2005, Montreal, Canada