An associative architecture for genetic algorithm-based machine learning

Machine-based learning will eventually be applied to solve real-world problems. In this work, an associative architecture teams up with hybrid AI algorithms to solve a letter prediction problem with promising results. This article describes an investigation and simulation of a massively parallel lea...

Full description

Saved in:
Bibliographic Details
Published in:Computer (Long Beach, Calif.) Vol. 27; no. 11; pp. 27 - 38
Main Author: Twardowski, K.
Format: Journal Article
Language:English
Published: New York IEEE 01.11.1994
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Algorithms
Artificial intelligence
Computational modeling
Computer architecture
Computer programming
Concurrent computing
Genetics
Inference algorithms
Learning systems
Machine learning
Machine learning algorithms
Production systems
ISSN:0018-9162, 1558-0814
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Machine-based learning will eventually be applied to solve real-world problems. In this work, an associative architecture teams up with hybrid AI algorithms to solve a letter prediction problem with promising results. This article describes an investigation and simulation of a massively parallel learning classifier system (LCS) that was developed from a specialized associative architecture joined with hybrid AI algorithms. The LCS algorithms were specifically invented to computationally match a massively parallel computer architecture, which was a special-purpose design to support the inferencing and learning components of the LCS. The LCS's computationally intensive functions include rule matching, parent selection, replacement selection and, to a lesser degree, data structure manipulation.< >
Bibliography:SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 14
ObjectType-Article-2
content type line 23
ISSN:0018-9162
1558-0814
DOI:10.1109/2.330041