DocumentCode
1115288
Title
An Adaptive Associative Memory Principle
Author
Kohonen, Teuvo
Author_Institution
Department of Technical Physics, Helsinki University of Technology
Issue
4
fYear
1974
fDate
4/1/1974 12:00:00 AM
Firstpage
444
Lastpage
445
Abstract
It is shown that an analog associative memory with optimal selectivity can be formed in adaptive processes which use learning algorithms related to the gradient method. The information is distributed throughout the memory by a matrix transform.
Keywords
Adaptive system, analog associative memory, associative recall, correlation matrix memory, distributed memory, learning system, pattern recognition, pseudoinverse matrix.; Associative memory; Circuits; Distributed computing; Gradient methods; Information systems; Learning systems; Pattern recognition; Physics computing; Quantum computing; Adaptive system, analog associative memory, associative recall, correlation matrix memory, distributed memory, learning system, pattern recognition, pseudoinverse matrix.;
fLanguage
English
Journal_Title
Computers, IEEE Transactions on
Publisher
ieee
ISSN
0018-9340
Type
jour
DOI
10.1109/T-C.1974.223960
Filename
1672553
Link To Document