Title :
Microcircuit learning nets: Hamming-distance behaviour
Author_Institution :
University of Kent at Canterbury, Electronics Laboratory, Canterbury, UK
Abstract :
A probabilistic method based on the Hamming distance is presented for calculating the pattern-recognition response of a class of single-layer microcircuit learning nets. The prediction of the behaviour of a 12-element machine is shown to agree with measured responses. The method is also used to explain the characteristics of nets trained on translated versions
Keywords :
learning systems; pattern recognition; probability;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19700092