Evolvable Cellular Classifiers for pattern Recognition

패턴 인식을 위한 진화 셀룰라 분류기

  • Ju, Jae-Ho (School of Electrical & Electronics Engineering, Chung-Ang University) ;
  • Shin, Yoon-Cheol (School of Electrical & Electronics Engineering, Chung-Ang University) ;
  • Kang, Hoon (School of Electrical & Electronics Engineering, Chung-Ang University)
  • Published : 2000.08.01

Abstract

A cellular automaton is well-known for self-organizing and dynamic behavions in the filed of artifial life. This paper addresses a new neuronic architecture called an evolvable celluar classifier which evolves with the genetic rules (chromosomes) in the non-uniform cellular automata. An evolvable cellular classifier is primarily based on cellular programming, but its mechanism is simpler becaise it utilizes only mutations for the main genetic operators and resmbles the Hopfield network. Therefore, the desirable bit-patterns could be obtained through evolutionary processes for just one individual agent, As a rusult, an evolvable hardware is derived which is applicable to clessification of bit-string information.

Keywords

References

  1. in Artificial Life Ⅱ, vol.Ⅹ of SFI Studies in the Science of Complexity v.Ⅱ no.Ⅹ Life at the edge of chaos C.G. Langton;C. Taylor(ed.);J.D. Farmer(ed.);S. Rasmussen(ed.)
  2. Theory of Self-Reproducing Automata J. von Neumann;A.W. Burks(ed.)
  3. On cellular automata, self-reproduction, the Garden of Eden and the game 'Life M. Gardner
  4. Cellular Automata E.F. Codd
  5. in Proceedings of IEEE $3_{rd}$ Int. Conf. on Evolutionary Computation (ICEC'96) Cam-Brain, ATR's billion neuron artificial brain project : A three year progress report H. deGaris
  6. Cellular Automata and Complexity : collected papers S. Wolfram
  7. Artificial Life : The Quest for a New Creation S. Levy
  8. Physica D v.75 Evolving cellular automata to perform computations : Mechanisms and impediments M. Mitchell;J.P. Crutchfield;P.T. Hraber
  9. Evolution of Parallel Cellular Machines : The Cellular Programming Approach M. Sipper
  10. in Proceedings of National Academic Science USA, Biophysics v.79 Neural networks and physical systems with emergent collective computational abilities J.J. Hopfield
  11. IEEE Trans. on Systems, Man, and Cybernetics v.18 no.1 Bidirectional Associative Memories B. Kosko
  12. IEEE Trans. on Neural Networks v.5 no.5 Multi-layer Associative Neural Networks : storage capacity vs. perfect recall H. Kang
  13. The Bell System Technical Journal v.27 The mathematical theory of communication C.E. Shannon
  14. VHDL Analysis and Modeling of Digital Systems Z. Navabi