Title :
Pattern separation in digital learning nets
Author :
Aitken, D.L.P. ; Bishop, J.M. ; Mitchell, R.J. ; Pepper, S.E.
Author_Institution :
Dept. of Cybernetics, Reading Univ., UK
fDate :
5/25/1989 12:00:00 AM
Abstract :
Pattern separation is a new technique in digital learning networks which can be used to detect state conflicts. This letter describes pattern separation in a simple single-layer network, and an application of the technique in networks with feedback.
Keywords :
learning systems; pattern recognition; Hamming distance; digital learning nets; feedback; pattern separation; single-layer network; state conflicts;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19890463
