Genetic-based machine learning using hardware accelerator

Authors:
Masaya Yoshikawa;Hidekazu Terai
Affiliations:
Department of Information Engineering, Meijo University, Tenpaku, Nagoya, Aichi, Japan;Department of VLSI System Design, Ritsumeikan University, Nojihigashi, Kusatsu, Shiga, Japan
Venue:
ICC'08 Proceedings of the 12th WSEAS international conference on Circuits
Year:
2008

Citing 3
Cited 0

Adaptation in natural and artificial systems

Adaptation in natural and artificial systems
HGA: a hardware-based genetic algorithm

FPGA '95 Proceedings of the 1995 ACM third international symposium on Field-programmable gate arrays
Genetic Algorithms in Search, Optimization and Machine Learning

Genetic Algorithms in Search, Optimization and Machine Learning

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper discusses new genetic-based learning system. The proposed learning system adopts new if-then rules for acquiring a strategy of the robots. Moreover, it introduces novel hardware accelerator in order to reduce simulation time, since the genetics-based machine learning requires very long computational time. Experiments using quasi-ecosystem demonstrate not only the effectiveness of the proposed learning algorithm, but also that of the proposed architecture of hardware accelerator.