DocumentCode :
445944
Title :
An associative memory for the on-line recognition and prediction of temporal sequences
Author :
Bose, J. ; Furber, S.B. ; Shapiro, J.L.
Author_Institution :
Sch. of Comput. Sci., Manchester Univ., UK
Volume :
2
fYear :
2005
fDate :
31 July-4 Aug. 2005
Firstpage :
1223
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 :
content-addressable storage; distributed memory systems; learning (artificial intelligence); associative memory; online recognition; prediction; temporal sequences; temporal sequences prediction; Associative memory; Computer science; Context modeling; Encoding; Neural networks; Numerical simulation; Predictive models; Read-write memory; Scalability; Shift registers;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2005. IJCNN '05. Proceedings. 2005 IEEE International Joint Conference on
Print_ISBN :
0-7803-9048-2
Type :
conf
DOI :
10.1109/IJCNN.2005.1556028
Filename :
1556028
Link To Document :
بازگشت