An associative architecture for genetic algorithm-based machine learning

Publisher Website
Google Scholar
Abstract
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.