Accession Number : AD0716462

Title :   A General Class of Layered, Trainable, Threshold Logic Networks for Pattern Classification,

Corporate Author : WASHINGTON UNIV SEATTLE DEPT OF ELECTRICAL ENGINEERING

Personal Author(s) : Francalangia,James L.

Report Date : DEC 1969

Pagination or Media Count : 129

Abstract : The system developed uses a three-layer network of TLE's, only one layer of which is made up of adaptive elements. Each network is modular, permitting individual primary subnet modules to be altered without affecting the partition realized by the remainder of the network. Training involves a modified error-correction rule for weight adjustment, and appropriate addition or deletion of decision elements. Heuristic procedures are developed to implement these features in the form of an adaptive program. The training process identifies the boundaries of populated regions of patternspace. Each net module defines a convex solution region described by a small set of hyperplanes. The nearest boundary classifying rule is introduced to categorize patterns lying outside populated regions. This classifying rule is shown to approach the accuracy of the nearest neighbor rule. (Author)

Descriptors :   (*LEARNING MACHINES, *PATTERN RECOGNITION), ARTIFICIAL INTELLIGENCE, COMPUTER PROGRAMMING, DIGITAL COMPUTERS, CORRECTIONS, THIN FILM STORAGE DEVICES, STOCHASTIC PROCESSES, ADAPTIVE SYSTEMS, THESES

Subject Categories : Computer Programming and Software
      Computer Hardware
      Bionics

Distribution Statement : APPROVED FOR PUBLIC RELEASE