
Accession Number : AD0645499
Title : NONLINEAR PREPROCESSING OF INPUTS TO LINEAR NEURAL NETS,
Corporate Author : BELL AEROSYSTEMS CO BUFFALO N Y
Personal Author(s) : Goerner,Johannes G. ; Gerhardt,L. A. ; Powell,F. D.
Report Date : OCT 1966
Pagination or Media Count : 55
Abstract : Discrimination of analog signal patterns by linear singlegain layer nets can be significantly improved by feeding the analog signals into preprocessors that convert each analog signal to a binary signal with m bits, thus increasing the number of gain elements from n to nm. The number of input vectors to which an arbitrarily desired net output can be assigned increases correspondingly from n to mn. This result holds for any binary converter with word length m independent of the code of the converter. The number increases further with the radix q if a qary preprocessor is employed. The common quantizer shows particular merits for practical applications as only one output line in any quantizer is active, thus allowing gain adjustments independent of each other within each quantizer. The combination of quantizer and linear net is reported on in detail. With a forced learningtype training algorithm, final gain values are shown to represent the difference of the conditional probabilities of the input pattern classes. The combination of quantizer and linear net instruments a type of likelihood ratio. With an errorcorrecting training algorithm, the final gains form a gain vector such that the error with respect to the desired output for each class becomes minimized in the least mean square sense. (Author)
Descriptors : (*BIONICS, DATA PROCESSING), NONLINEAR SYSTEMS, INPUT OUTPUT DEVICES, ADAPTIVE SYSTEMS, ANALOG SYSTEMS, CODING, LEARNING MACHINES, PROCESSING, NETWORKS
Subject Categories : Computer Hardware
Computer Systems
Bionics
Distribution Statement : APPROVED FOR PUBLIC RELEASE