Abstract
This paper describes Evolvable Hardware (EHW) and its applications to pattern recognition and fault-torelant systems. EHW can change its own hardware structure to adapt to the environment whenever environmental changes (including hardware malfunction) occur. EHW is implemented on a PLD(Programmable Logic Device)-like device whose architecture can be altered by re-programming the architecture bits. Through genetic algorithms, EHW finds the architecture bits which adapt best to the environment, and changes its hardware structure accordingly.
Two applications are described: the the pattern recognitionsystem and the V-shape ditch tracer with fault-tolerant circuit. First we show the exclusive-OR circuit can be learned by EHW successfully. Then the pattern recognition system with EHW is described. The objective is to take the place of neural networks, solving its weakness such as readability of learned results and the execution speed. The results show that EHW works as a hard-wired pattern recognizer with such the robustness as neural nets. The second application is the V-shape ditch tracer as part of a prototypical welding robot. EHW works as the backup of the control logic circuit for the tracing, although the EHW is not given any information about the circuit. Once a hardware error occurs, EHW takes over the malfunctioning circuit.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
Aleksander I., “Reinventing Man” Penguin Books, EnNgland, 1984.
Armstrong W. and Gecsei J. “Adaptation Algorithms for Binary Tree Network” IEEE Trans. on SMC, Vol. SMC-9, No.5, 1979.
de Garis, H. “An Artificial Brain — ATR's CAM-Brain Project Aims to Build/Evolve an Artificial Brain with a Million Neural Net Modules Inside a Trillion Cell Cellular Atutomata Machine” New Genreration Computing, OHMSHA.LTD and Springer-Verlag, 12, pp.215–221 (1994).
Goldberg D., “Genetic Algorithms in Search, Optimization, and Machine Learning” Addison Wesley, 1989.
Henmi H. et al “Development and Evolution of Hardware Behaviors” Proc. of Artificial Life IV, MIT Press, 1994.
Higuchi T. et al., “Evolvable Hardware with Genetic Learning” in Proc. of Simulated Adaptive Behavir, MIT Press, 1993.
Higuchi T. et al., “Evolvable Hardware with Genetic Learning” in Massively Parallel Artificial Intelligence(eds. H. Kitano), MIT Press, 1994.
Itoh, S. “Application of MDL principle to pattern classification problems” (in Japanese),JSAI journal, Vol.7, No.4, 1992.
Iwata M. et al. “Consideration on implementation of pattern recognition system based on evolvable hardware” ETL technical report, Oct. 1995.
Kajitani I. et al. “Variable length genetic algorithms for evolvable hardware” ETL technical report, Oct. 1995.
Kitano H. “Evolvable Hardware with Development” in this proceedings (EVOLVE95), Oct. 1995.
Koza J., “Genetic Programming: On the Programming of Computers by means of Natural Selection” MIT Press, 1992.
Lattice Semiconductor Corporation, “GAL Data Book” 1990
P.Marchal,C.Piguet,D.Mange,A.Stauffer,S.Durand “Embryological development on silicon” Artificial Life IV, MIT Press, 1994.
Rissanen, J. Stochastic complexity in statistical inquiry World Scientific Series in COmputer Science, Vol.15, 1989.
Rosenblatt F., “Principles of Neurodynamics” Spartan Books, New York, 1962.
Thompson A., “Evolving electronic robot controllers that exploit hardware resources” Proc. of 3rd European Conf. on Artificial Life, 1995.
Wilson S., “Classifier Systems and the Animat Problem” Machine Learning 2, 199–228, 1987.
Xilinx Semiconductor Corporation, “LCA Data Book” 1994.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Higuchi, T. et al. (1996). Evolvable Hardware and its application to pattern recognition and fault-tolerant systems. In: Sanchez, E., Tomassini, M. (eds) Towards Evolvable Hardware. Lecture Notes in Computer Science, vol 1062. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61093-6_6
Download citation
DOI: https://doi.org/10.1007/3-540-61093-6_6
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61093-9
Online ISBN: 978-3-540-49947-3
eBook Packages: Springer Book Archive