Accession Number : AD0427840

Title :   DETERMINATION AND DETECTION OF FEATURES IN PATTERNS,

Corporate Author : CORNELL UNIV ITHACA N Y

Personal Author(s) : Block,H. D. ; Nilsson,N. J. ; Duda,R. W.

Report Date : DEC 1963

Pagination or Media Count : 52

Abstract : Feature determination as a method of training the first layer of weights in a two layer learning machine (Perceptron) is investigated. The problem is viewed as one of examining a set of patterns and determining a set of simpler patterns, or features, so that each of the original patterns can be formed by superposing the features. While the general problem of finding a minimal set of features was not solved, two algorithms were given that solve the problem for restricted pattern sets. (Author)

Descriptors :   (*TEACHING MACHINES, TRAINING), (*ARTIFICIAL INTELLIGENCE, TEACHING MACHINES), (*TRAINING, PATTERN RECOGNITION), (*PATTERN RECOGNITION, DETECTION), ALGEBRA, MATHEMATICAL ANALYSIS, PROGRAMMING LANGUAGES, DETERMINATION

Distribution Statement : APPROVED FOR PUBLIC RELEASE