Advertisement

Promises and challenges of Evolvable hardware

  • Xin Yao
  • Tetsuya Higuchi
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1259)

Abstract

Evolvable hardware (EHW) has attracted increasing attentions since early 1990's with the advent of easily reconfigurable hardware such as field programmable logic array (FPGA). It promises to provide an entirely new approach to complex electronic circuit design and new adaptive hardware. EHW has been demonstrated to be able to perform a wide range of tasks from pattern recognition to adaptive control. However, there are still many fundamental issues in EHW remain open. This paper reviews the current status of EHW, discusses the promises and possible advantages of EHW, and indicates the challenges we must meet in order to develop practical and large-scale EHW.

Keywords

Genetic Algorithm Genetic Programming Logic Gate Circuit Design Fitness Evaluation 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    A. J. Hirst. Notes on the evolution of adaptive hardware. In I. Parmee, editor, Proc. of the 2nd Int. Conf. on Adaptive Computing in Engineering & Design (ACEDC96), 1996.Google Scholar
  2. [2]
    T. Higuchi, M. Iwata, I. Kajitani, H. Iba, T. Furuya, and B. Manderick. Evolvable hardware and its applications to pattern recognition and faulttolerant systems. In E. Sanchez and M. Tomassini, editors, Towards Evolvable Hardware: The Evolutionary Engineering Approach, Lecture Notes in Computer Science, Vol. 1062, pages 118–135. Springer-Verlag, 1996.Google Scholar
  3. [3]
    P. Graham and B. Nelson. A hardware genetic algorithm for the traveling salesman problem on splash 2. In Proc. of the 5th Int. Workshop on Field Programmable Logic and Applications, Oxford, England, pages 352–361, August 1995.Google Scholar
  4. [4]
    S. D. Scott, A. Samal, and S. Seth. HGA: A hardware based genetic algorithm. In Proc. of ACM/SIGDA 3rd Int. Symp. on FPGA's, pages 53–59, 1995.Google Scholar
  5. [5]
    M. Salami and G. Cain. Implementation of genetic algorithms on reprogrammable architectures. In X. Yao, editor, Proc. of the Eighth Australian Joint Conference on Artificial Intelligence (AI'95), page 581. World Scientific Publ. Co., Singapore, 1995.Google Scholar
  6. [6]
    H. de Garis. LSL evolvable hardware workshop report. Technical report, ATR, Japan, October 1995.Google Scholar
  7. [7]
    M. P. Fourman. Compaction of symbolic layout using genetic algorithms. In J. J. Grefenstette, editor, Proc. of the First Int'l Conf. on Genetic Algorithms and Their Applications, pages 141–153. Carnegie-Mellon University, 1985.Google Scholar
  8. [8]
    J. Cohoon and W. Paris. Genetic placement. In Proc. of Int'l Conf. on CAD, pages 422–425. IEEE Press, New York, NY 10017-2394, 1986.Google Scholar
  9. [9]
    R. M. Kling and P. Banerjee. ESP: Placement by simulated evolution. IEEE Trans, on CAD, CAD-8:245–256, 1989.Google Scholar
  10. [10]
    H. Hemmi, J. Mizoguchi, and K. Shimohara. Development and evolution of hardware behaviours. In R. Brooks and P. Maes, editors, Artificial Life IV: Proc. of the 4th Int. Workshop on the Synthesis and Simulation of Living Systems, pages 371–376. MIT Press, 1994.Google Scholar
  11. [11]
    J. R. Koza. Genetic Programming. The MIT Press, Cambridge, Mass., 1992.Google Scholar
  12. [12]
    J. R. Koza. Genetic Programming II. The MIT Press, Cambridge, Mass., 1994.Google Scholar
  13. [13]
    P.A. Whigham. Grammatically-based genetic programming. In J.Rosca, editor, Proc. of the Workshop on Genetic Programming: From Theory to Real-World Applications, pages 33–41. Morgan Kaufmann Publ., July 1995.Google Scholar
  14. [14]
    P.A. Whigham. Inductive bias and genetic programming. In Proc. of the 1st Int. Conf. on Genetic Algorithms in Engineering Systems: Innovations and Applications, pages 461–466. IEE, UK, Sept. 1995.Google Scholar
  15. [15]
    P.A. Whigham and R. McKay. Genetic approaches to learning recursive relations. In X. Yao, editor, Progress in Evolutionary Computation, Lecture Notes in Artificial Intelligence, Vol. 956, pages 17–27. Springer-Verlag, Heidelberg, 1995.Google Scholar
  16. [16]
    P.A. Whigham. A schema theorem for context-free grammars. In Proc. of the 1995 IEEE Int. Conf. on Evolutionary Computation (ICEC'95), volume 1, pages 178–182. IEEE Press, Piscatawa, NJ, USA, December 1995.Google Scholar
  17. [17]
    W. Kruiskamp and D. Leenaerts. DARWIN: CMOS opamp synthesis by means of a genetic algorithm. In Proc. of the 32nd Design Automation Conference, pages 433–438. ACM Press, New York, NY, USA, 1995.Google Scholar
  18. [18]
    J. R. Koza, F. H. Bennett III, D. Andre, and M. A. Keane. Four problems for which a computer program evolved by genetic programming is competitive with human performance. In Proc. of the 1996 IEEE Int. Conf. on Evolutionary Computation (ICEC'96), pages 1–10. IEEE Press, Piscatawa, NJ, USA, May 1996.Google Scholar
  19. [19]
    J. R. Koza, D. Andre, F. H Bennett III, and M. A. Keane. Use of automatically defined functions and architecture-altering operations in automated circuit synthesis using genetic programming. In Proc. of the Genetic Programming 1996 Conference (GP'96). The MIT Press, 1996.Google Scholar
  20. [20]
    J. R. Koza, F. H Bennett III, D. Andre, and M. A. Keane. Automated WYWIWYG design of both the topology and component values of electrical circuits using genetic programming. In Proc. of the Genetic Programming 1996 Conference (GP'96). The MIT Press, 1996.Google Scholar
  21. [21]
    X. Yao. Evolutionary artificial neural networks. In A. Kent and J. G. Williams, editors, Encyclopedia of Computer Science and Technology, volume 33, pages 137–170. Marcel Dekker Inc., New York, NY 10016, 1995.Google Scholar
  22. [22]
    T. Higuchi, T. Niwa, T. Tanaka, H. Iba, H. de Garis, and T. Furuya. Evolving hardware with genetic learning: A first step towards building a Darwin machine. In Proc. of 2nd Int. Conf. on the Simulation of Adaptive Behaviour (SAB92), pages 417–424. MIT Press, 1992.Google Scholar
  23. [23]
    T. Higuchi, H. Iba, and B. Manderick. Evolvable hardware. In H. Kitano and J. Hendler, editors, Massively Parallel Artificial Intelligence, pages 398–421. MIT Press, 1994.Google Scholar
  24. [24]
    T. Higuchi, M. Iwata, I. Kaijitani, M. Murakawa, S. Yoshizawa, and T. Furuya. Hardware evolution at gate and function level. In Proc. of the Int. Conf. on Biologically Inspired Autonomous Systems: Computation, Cognition and Action, Durham, NC, USA, 4–5 March 1996.Google Scholar
  25. [25]
    A. Thompson, I. Harvey, and P. Husbands. Unconstrained evolution and hard consequences. In E. Sanchez and M. Tomassini, editors, Towards Evolvable Hardware: The Evolutionary Engineering Approach, Lecture Notes in Computer Science, Vol. 1062, pages 136–165. Springer-Verlag, 1996.Google Scholar
  26. [26]
    A. Thompson. Silicon evolution. In Proc. of the Int. Conf. on Genetic Programming (GP'96), page To appear, 1996.Google Scholar
  27. [27]
    M. Murakawa, S. Yoshizawa, I. Kajitani, T. Furuya, M. Iwata, and T. Higuchi. Hardware evolution at function level. In Proc. of the International Conference on Parallel Problem Solving from Nature (PPSN'96), page Accepted, 1996.Google Scholar
  28. [28]
    X. Yao. Evolutionary artificial neural networks. International Journal of Neural Systems, 4(3):203–222, 1993.Google Scholar
  29. [29]
    X. Yao and Y. Liu. Evolving artificial neural networks for medical applications. In Proc. of 1995 Australia-Korea Joint Workshop on Evolutionary Computation, pages 1–16. KAIST, Taejon, Korea, September 1995.Google Scholar
  30. [30]
    X. Yao and Y. Liu. A new evolutionary system for evolving artificial neural networks. IEEE Trans, on Neural Networks, 1995. Submitted.Google Scholar
  31. [31]
    X. Yao and Y. Liu. Towards designing artificial neural networks by evolution. In Proc. of Int. Symp. on Artificial Life and Robotics (AROB), Beppu, Oita, Japan, pages 265–268, 18–20 February 1996.Google Scholar
  32. [32]
    X. Yao and Y. Liu. Evolving artificial neural networks through evolutionary programming. In P. Angeline and T. Back, editors, Evolutionary Programming V: Proc. of the Fifth Annual Conference on Evolutionary Programming, page To appear. MIT Press, 1996.Google Scholar
  33. [33]
    X. Yao and Y. Liu. Evolutionary artificial neural networks that learn and generalise well. In 1996 IEEE International Conference on Neural Networks, Washington, DC, USA. IEEE Press, New York, NY, 3–6 June 1996. Accepted.Google Scholar
  34. [34]
    Y. Liu and X. Yao. A population-based learning algorithm which learns both architectures and weights of neural networks. Chinese Journal of Advanced Software Research (Allerton Press, Inc., New York, NY 10011), 3(1):54–65, 1996.Google Scholar
  35. [35]
    M. A. Rosenman. An evolutionary model for non-routine design. In X. Yao, editor, Proc. of the Eighth Australian Joint Conference on Artificial Intelligence (AI'95), pages 363–370. World Scientific Publ. Co., Singapore, 1995.Google Scholar
  36. [36]
    K. Sims. Artificial evolution for computer graphics. Computer Graphics, 25(4):319–328, 1991.Google Scholar
  37. [37]
    J. J. Grefenstette. Incorporating problem specific knowledge into genetic algorithms. In L. Davis, editor, Genetic Algorithms and Simulated Annealing, chapter 4, pages 42–60. Morgan Kaufmann, San Mateo, CA, 1987.Google Scholar
  38. [38]
    L. Davis. Handbook of Genetic Algorithms. Van Nostrand Reinhold, New York, NY 10003, 1991.Google Scholar
  39. [39]
    H. Hemmi, J. Mizoguchi, and K. Shimohara. Development and evolution of hardware behaviors. In E. Sanchez and M. Tomassini, editors, Towards Evolvable Hardware: The Evolutionary Engineering Approach, Lecture Notes in Computer Science, Vol. 1062, pages 250–265. Springer-Verlag, 1996.Google Scholar
  40. [40]
    J. Mizoguchi, H. Hemmi, and K. Shimohara. Production genetic algorithms for automated hardware design through an evolutionary process. In Z. Michalewicz et al., editor, Proc. of the First IEEE Conf. on Evolutionary Computation (ICEC'94), Vol. I, pages 661–664. IEEE Press, New York, NY 10017-2394, 1994.Google Scholar
  41. [41]
    A. Thompson. Evolving electronic robot controllers that exploit hardware resources. In Proc. of the 3rd European Conf. on Artificial Life (ECAL95), pages 640–656. Springer-Verlag, 1995.Google Scholar
  42. [42]
    M. Iwata, I. Kajitani, H. Yamada, H. Iba, and T. Higuchi. A pattern recognition system using evolvable hardware. In Proc. of the International Conference on Parallel Problem Solving from Nature (PPSN'96), page Accepted, 1996.Google Scholar
  43. [43]
    I. Kajitani, T. Hoshino, M. Iwata, and T. Higuchi. Variable length chromosome GA for evolvable hardware. In Proc. of the 1996 IEEE Int. Conf. on Evolutionary Computation (ICEC'96), pages 443–447. IEEE Press, Piscatawa, NJ, USA, May 1996.Google Scholar
  44. [44]
    D. E. Goldberg, K. Deb, H. Kargupta, and G. Harik. Rapid, accurate optimization of difficult problems using fast messy genetic algorithms. In S. Forrest, editor, Proc. of the 5th Int. Conf. on Genetic Algorithms (ICGA '93), pages 56–64. Morgan Kaufmann, 1993.Google Scholar
  45. [45]
    J. Rissanen. Stochastic complexity in statistical inquiry. World Scientific, Singapore, 1989.Google Scholar
  46. [46]
    X. Yao. Evolution of connectionist networks. In T. Dartnall, editor, Preprints of the Int'l Symp. on AI, Reasoning & Creativity, pages 49–52, Queensland, Australia, 1991. Griffith University.Google Scholar
  47. [47]
    X. Yao. A review of evolutionary artificial neural networks. International Journal of Intelligent Systems, 8(4):539–567, 1993.Google Scholar
  48. [48]
    Y. Liu and X. Yao. Evolutionary design of artificial neural networks with different nodes. In Proc. of the 1996 IEEE Int'l Conf. on Evolutionary Computation (ICEC'96), Nagoya, Japan, pages 670–675. IEEE Press, New York, NY 10017-2394, 1996.Google Scholar
  49. [49]
    H. Iba, H. de Garis, and T. Sato. A numerical approach to genetic programming for system identification. Evolutionary Computation, 3(4):417–452, 1996.Google Scholar
  50. [50]
    D. Mange and A. Stauffer. Introduction to embryonics: Towards new self-repairing and self-reproducing hardware based on biological-like properties. In N. Magnenat Thalmann and D. Thalmann, editors, Artificial Life and Virtual Reality, pages 61–72. John Wiley, Chichester, England, 1994.Google Scholar
  51. [51]
    P. Marchal, C. Piguet, D. Mange, A. Stauffer, and S. Durand. Achieving von Neumann's dream: Artificial life on silicon. In Proc. of the IEEE International Conference on Neural Networks (ICNN'94), Volume IV, pages 2321–2326, 1994.Google Scholar
  52. [52]
    S. Durand, A. Stauffer, and D. Mange. Biodule: An introduction to digital biology. Technical Report Preliminary Report, Logic Systems Laboratory, The Swiss Federal Institute of Technology, Lausanne, September 1994.Google Scholar
  53. [53]
    D. Mange, S. Durand, E. Sanchez, A. Stauffer, G. Tempesti, P. Marchal, and C. Piguet. A new self-reproducing automaton based on a multi-cellular organization. Technical Report 95/114, Logic Systems Laboratory, The Swiss Federal Institute of Technology, Lausanne, April 1995.Google Scholar
  54. [54]
    J. von Neumann. The Theory of Self-Reproducing Automata. University of Illinois Press, Urbana, 1966.Google Scholar
  55. [55]
    H. de Garis. Circuits of production rule GenNets: the genetic programming of artificial nervous systems. In R. F. Albrecht, C. R. Reeves, and N. C. Steele, editors, Proc. of the Int. Conf. on Artificial Neural Nets and Genetic Algorithms, Innsbruck, Austria, pages 699–705. Springer-Verlag/Wien, 1993.Google Scholar
  56. [56]
    H. de Garis. Evolvable hardware: Genetic programming of a darwin machine. In R. F. Albrecht, C. R. Reeves, and N. C. Steele, editors, Proc. of the Int. Conf. on Artificial Neural Nets and Genetic Algorithms, Innsbruck, Austria, pages 441–449. Springer-Verlag/Wien, 1993.Google Scholar
  57. [57]
    H. de Garis. An artificial brain. New Generation Computing, 12:215–221, 1994.Google Scholar
  58. [58]
    H. de Garis. CAM-BRAIN — the evolutionary engineering of a billion neuron artificial brain by 2001 which grows/evolves at electronic speeds inside a cellular automata machine (CAM). In D. W. Pearson, N. C. Steele, and R. F. Albrecht, editors, Proc. of the Int. Conf. on Artificial Neural Nets and Genetic Algorithms, Alés, France, pages 84–87. Springer-Verlag/Wien, 1995.Google Scholar
  59. [59]
    H. de Garis. CAM-BRAIN: the evolutionary engineering of a billion neuron artificial brain by 2000 which grows/evolves at electronic speeds inside a cellular automata machine (cam). In E. Sanchez and M. Tomassini, editors, Towards Evolvable Hardware: The Evolutionary Engineering Approach, Lecture Notes in Computer Science, Vol. 1062, pages 76–98. Springer-Verlag, 1996.Google Scholar
  60. [60]
    H. de Garis. CAM-BRAIN issues: implementation and performance-scaling issues concerning the genetic programming of a cellular automata based artificial brain. In Proc. of the IEEE International Conference on Neural Networks (ICNN'94), Volume III, pages 1714–1720, 1994.Google Scholar
  61. [61]
    V. Kantabutra. On hardware for computing exponential and trigonometric functions. IEEE Trans, on Computers, 45(3):328–339, 1996.Google Scholar
  62. [62]
    C.-A. Chen and S. K. Gupta. BIST test pattern generators for two-pattern testing — theory and design algorithms. IEEE Trans, on Computers, 45(3):257–269, 1996.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1997

Authors and Affiliations

  • Xin Yao
    • 1
  • Tetsuya Higuchi
    • 2
  1. 1.Computational Intelligence Group, School of Computer Science University CollegeThe University of New South Wales Australian Defence Force AcademyCanberraAustralia
  2. 2.Computation Models SectionElectrotechnical LaboratoryIbarakiJapan

Personalised recommendations