Adaptive pattern recognition using goal seeking neurons

This paper defines a novel Boolean neuron model which is particularly suited to practical pattern recognition tasks. It achieves its learning with a single pass of the training data and pattern classification capability emerges from the use of local low level goals.

Saved in:
Bibliographic Details
Published inPattern recognition letters Vol. 12; no. 3; pp. 131 - 138
Main Authors Filho, E.C.D.B.C., Fairhurst, M.C., Bisset, D.L.
Format Journal Article
LanguageEnglish
Published Amsterdam Elsevier B.V 1991
Elsevier
Subjects
Applied sciences
Artificial intelligence
Computer science; control theory; systems
Exact sciences and technology
fast learning
Neural networks
Pattern recognition. Digital image processing. Computational geometry
RAM-based neurons
fast learning
Neural networks
RAM-based neurons
Learning
Acquisition process
Models
Pattern recognition
Neural network
Algorithm
Adaptive method
Online AccessGet full text

Cover

More Information
Summary:This paper defines a novel Boolean neuron model which is particularly suited to practical pattern recognition tasks. It achieves its learning with a single pass of the training data and pattern classification capability emerges from the use of local low level goals.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0167-8655
1872-7344
DOI:10.1016/0167-8655(91)90040-S