Accession Number : AD0658527
Title : RESEARCH ON SELF-ORGANIZING MACHINES.
Descriptive Note : Final rept.,
Corporate Author : STANFORD RESEARCH INST MENLO PARK CALIF
Personal Author(s) : Duda,Richard O.
Report Date : SEP 1967
Pagination or Media Count : 31
Abstract : This report reviews the results of a program of research on self-organizing machines. This research was primarily directed at establishing the conditions under which iterative machine-learning procedures can be guaranteed to converge. The most significant result of this effort was the development of a fairly complete theory of the linear machine, an important trainable multicategory pattern classifier. Theoretical results are summarized and related to the present state of research in pattern recognition. (Author)
Descriptors : (*PATTERN RECOGNITION, MATHEMATICAL MODELS), (*LEARNING MACHINES, PATTERN RECOGNITION), ACCURACY, MAPPING(TRANSFORMATIONS), CONVERGENCE, ITERATIONS, TRAINING, CLASSIFICATION
Subject Categories : Information Science
Distribution Statement : APPROVED FOR PUBLIC RELEASE