Title :
Improved Hamming-distance analysis for digital learning networks
Author_Institution :
University of Kent at Canterbury, Electronics Laboratories, Canterbury, UK
Abstract :
A method for calculating the response of a single-layer network pattern-recognition system is presented. To obtain accurate prediction of the network response, it is necessary to consider the Hamming distances between training patterns. The method is demonstrated with reference to an alphanumeric recognition test.
Keywords :
learning systems; pattern recognition; random-access storage; Hamming distance analysis; alphanumeric recognition test; digital learning networks; random access memories; single layer network pattern recognition system;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19770110
