Result Details

Coevolutionary Cartesian Genetic Programming in FPGA

HRBÁČEK, R.; DRAHOŠOVÁ, M. Coevolutionary Cartesian Genetic Programming in FPGA. Advances in Artificial Life, ECAL 2013, Proceedings of the Twelfth European Conference on the Synthesis and Simulation of Living Systems. Cambridge: MIT Press, 2013. p. 431-438. ISBN: 978-0-262-31709-2.
Type
conference paper
Language
English
Authors
Abstract

In this paper, a hardware platform for coevolutionary cartesian genetic programming is proposed. The proposed two-population coevolutionary algorithm involves the implementation of search algorithms in two MicroBlaze soft processors (one for each population) interconnected by the AXI bus in Xilinx Virtex 6 FPGA. Candidate programs are evaluated in a domain-specific virtual reconfigurable circuit incorporated into custom MicroBlaze peripheral. Experimental results in the task of evolutionary image filter design show that we can achieve a significant speed-up (up to 58) in comparison with a highly optimized software implementation.

Keywords

Cartesian genetic programming, coevolutionary algortihms, fitness modeling, hardware acceleration, FPGA.

URL
Published
2013
Pages
431–438
Proceedings
Advances in Artificial Life, ECAL 2013, Proceedings of the Twelfth European Conference on the Synthesis and Simulation of Living Systems
Conference
12th European Conference on Artificial Life
ISBN
978-0-262-31709-2
Publisher
MIT Press
Place
Cambridge
DOI
BibTeX
@inproceedings{BUT103495,
  author="Radek {Hrbáček} and Michaela {Drahošová}",
  title="Coevolutionary Cartesian Genetic Programming in FPGA",
  booktitle="Advances in Artificial Life, ECAL 2013, Proceedings of the Twelfth European Conference on the Synthesis and Simulation of Living Systems",
  year="2013",
  pages="431--438",
  publisher="MIT Press",
  address="Cambridge",
  doi="10.7551/978-0-262-31709-2-ch062",
  isbn="978-0-262-31709-2",
  url="http://mitpress.mit.edu/sites/default/files/titles/content/ecal13/ch062.html"
}
Projects
Advanced secured, reliable and adaptive IT, BUT, Vnitřní projekty VUT, FIT-S-11-1, start: 2011-01-01, end: 2013-12-31, completed
Natural Computing on Unconventional Platforms, GACR, Standardní projekty, GAP103/10/1517, start: 2010-01-01, end: 2013-12-31, running
Research groups
Departments
Back to top