A pattern recognition program that generates, evaluates, and adjusts its own operators

Authors:
Leonard Uhr;Charles Vossler
Affiliations:
University of Michigan, Ann Arbor, Michigan;System Development Corporation, Santa Monica, California
Venue:
IRE-AIEE-ACM '61 (Western) Papers presented at the May 9-11, 1961, western joint IRE-AIEE-ACM computer conference
Year:
1961

Citing 3
Cited 7

Machine perception of printed and handwritten forms by means of procedures for assessing and recognizing gestalts

ACM '59 Preprints of papers presented at the 14th national meeting of the Association for Computing Machinery
Pattern recognition and reading by machine

IRE-AIEE-ACM '59 (Eastern) Papers presented at the December 1-3, 1959, eastern joint IRE-AIEE-ACM computer conference
Recognition of sloppy, hand-printed characters

IRE-AIEE-ACM '60 (Western) Papers presented at the May 3-5, 1960, western joint IRE-AIEE-ACM computer conference

Nonorthogonal Projections for Feature Extraction in Pattern Recognition

IEEE Transactions on Computers
Layered "Recognition Cone" Networks That Preprocess, Classify, and Describe

IEEE Transactions on Computers
Abstract shape recognition by machine

AFIPS '61 (Eastern) Proceedings of the December 12-14, 1961, eastern joint computer conference: computers - key to total systems control
Real time recognition of hand-drawn characters

AFIPS '64 (Fall, part I) Proceedings of the October 27-29, 1964, fall joint computer conference, part I
The learning of parameters for generating compound characterizers for pattern recognition

IJCAI'69 Proceedings of the 1st international joint conference on Artificial intelligence
DECIDER-1: a system that chooses among different types of acts

IJCAI'73 Proceedings of the 3rd international joint conference on Artificial intelligence
Computer-automated design of multifont print recognition logic

IBM Journal of Research and Development

Quantified Score

Hi-index	0.01

Visualization

Abstract

This paper describes an attempt to make use of machine learning or self-organizing processes in the design of a pattern-recognition program. The program starts not only without any knowledge of specific patterns to be input, but also without any operators for processing inputs. Operators are generated and refined by the program itself as a function of the problem space and of its own successes and failures in dealing with the problem space. Not only does the program learn information about different patterns, it also learns or constructs, in part at least, a secondary code appropriate for the analysis of the particular set of patterns input to it.