Skip to main content
Log in

A Scalable Approach to Evolvable Hardware

  • Published:
Genetic Programming and Evolvable Machines Aims and scope Submit manuscript

Abstract

Evolvable Hardware (EHW) has been proposed as a new method for designing systems for complex real-world applications. However, so far, only relatively simple systems have been shown to be evolvable. In this paper, it is proposed that concepts from biology should be applied to EHW techniques to make EHW more applicable to solving complex problems. One such concept has led to the increased complexity scheme presented, where a system is evolved by evolving smaller sub-systems. Experiments with two different tasks illustrate that inclusion of this scheme substantially reduces the number of generations required for evolution. Further, for the prosthesis control task, the best performance is obtained by the novel approach. The best circuit evolved performs better than the best trained neural network.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

References

  1. O. Aaserud and I. R. Nielsen, “Trends in current analog design: A panel debate,” Analog Integrated Circuits and Signal Processing, vol. 7, no. 1, pp. 5—9, 1995.

    Google Scholar 

  2. R. A. Brooks, C. Breazeal (Ferrell), R. Irie, C. Kemp, M. Marjanovic, B. Scassellati, and M. Williamson, “Alternative essences of intelligence,” in Proc. 15th National Conf. Artif. Intell. (AAAI-98), AAAI Press, 1998, pp. 961—976.

  3. E. Cantu-Paz, “A survey of parallel genetic algorithms,” Calculateurs Paralleles, Reseaux et Systems Repartis, vol. 10, no. 2, pp. 141—171, 1998.

    Google Scholar 

  4. J. Chavas, C. Corne, P. Horvai, J. Kodjabachian, and J.-A. Meyer, “Incremental evolution of neural controllers for robust obstacle-avoidance in Khepera,” in Proc. First European Workshop on Evolutionary Robotics, EvoRobot98, volume 1468 of Lecture Notes in Computer Science, P. Husbands and J.-A. Meyer (eds.), Springer-Verlag, 1998, pp. 227—247.

  5. P. Darwen and X. Yao, “Automatic modularization by speciation,” in Proc. of 1996 IEEE International Conf. Evolutionary Computation, 1996, pp. 88—93.

  6. S. Fuji, “Development of prosthetic hand using adaptable control method for human characteristics,” in Proc. Fifth Int. Conf. Intell. Autonomous Systems, 1998, pp. 360—367.

  7. D. Goldberg, Genetic Algorithms in Search, Optimization, and Machine Learning, Addison—Wesley, 1989.

  8. T. Higuchi, M. Iwata, I. Kajitani, H. Iba, Y. Hirao, B. Manderick, and T. Furuya, “Evolvable hardware and its applications to pattern recognition and fault-tolerant systems,” in Towards Evolvable Hardware: The evolutionary Engineering Approach, volume 1062 of Lecture Notes in Computer Science, E. Sanchez and M. Tomassini (eds.), Springer-Verlag, 1996, pp. 118—135.

  9. W. D. Hillis, “Co-evolving parasites improve simulated evolution as an optimization procedure,” Physica D, vol. 42, nos. 1—3, pp. 228—234, 1990.

    Google Scholar 

  10. M. Iwata, I. Kajitani, H. Yamada, H. Iba, and T. Higuchi, “A pattern recognition system using evolvable hardware,” in Proc. Parallel Problem Solving from Nature IV (PPSN IV), volume 1141 of Lecture Notes in Computer Science, Springer-Verlag, September 1996, pp. 761—770.

    Google Scholar 

  11. K. A. De Jong and M. A. Potter, “Evolving complex structures via co-operative coevolution,” in Proc. Fourth Ann. Conf. Evolutionary Programming, MIT Press, 1995, pp. 307—317.

  12. I. Kajitani, T. Hoshino, N. Kajihara, M. Iwata, and T. Higuchi, “An evolvable hardware chip and its application as a multi-function prosthetic hand controller,” in Proc. 16th National Conf. Artif. Intell. (AAAI-99), 1999, pp. 182—187.

  13. I. Kajitani, T. Hoshino, D. Nishikawa, H. Yokoi, S. Nakaya, T. Yamauchi, T. Inuo, N. Kajihara, M. Iwata, D. Keymeulen, and T. Higuchi, “A gate-level EHW chip: Implementing GA operations and reconfigurable hardware on a single LSI,” in Evolvable Systems: From Biology to Hardware. Second International Conference, ICES 98, volume 1478 of Lecture Notes in Computer Science, M. Sipper et al. (eds.), Springer-Verlag, 1998, pp. 1—12.

  14. J. R. Koza, Genetic Programming II: Automatic Discovery of Reusable Programs, The MIT Press, 1994.

  15. W.-P. Lee, J. Hallam, and H. H. Lund, “Learning complex robot behaviours by evolutionary computing with task decomposition,” in Learning Robots: Proc. 6th European Workshop, EWLR-6 Brighton, volume 1545 of Lecture Notes in Artificial Intelligence, A. Birk and J. Demiris (eds.), Springer-Verlag, 1997, pp. 155—172.

  16. W. Liu, M. Murakawa, and T. Higuchi, “ATM cell scheduling by function level evolvable hardware,” in Evolvable Systems: From Biology to Hardware. First International Conference, ICES 96, volume 1259 of Lecture Notes in Computer Science, T. Higuchi et al. (eds.), Springer-Verlag, 1997, pp. 180—192.

  17. P. Marchal, C. Piguet, D. Mange, A. Stauffer, and S. Durand, “Embryological development on silicon,” in Artificial Life IV, R. Brooks and P. Maes (eds.), MIT Press, 1994, pp. 365—370.

  18. J. F. Miller, “Digital filter design at gate-level using evolutionary algorithms,” in Proc. Genetic and Evolutionary Computation Conf. (GECCO'99), W. Banzhaf et al. (eds.), Morgan Kaufmann, 1999, pp. 1127—1134.

  19. J. F. Miller and P. Thomson, “Aspects of digital evolution: Geometry and learning,” in Evolvable Systems: From Biology to Hardware. Second Int. Conf., ICES 98, volume 1478 of Lecture Notes in Computer Science, M. Sipper et al. (eds.), Springer-Verlag, 1998, pp. 25—35.

  20. J. F. Miller, D. Job, and V. K. Vassilev, “Principles in the evolutionary design of digital circuits— Part I,” J. Genetic Programming and Evolvable Machines, vol. 1, no. 1, pp. 8—35, 2000.

    Google Scholar 

  21. M. Murakawa, S. Yoshizawa, I. Kajitani, T. Furuya, M. Iwata, and T. Higuchi, “Hardware evolution at function level,” in Proc. Parallel Problem Solving from Nature IV (PPSN IV), volume 1141 of Lecture Notes in Computer Science, Springer-Verlag, September 1996, pp. 62—71.

    Google Scholar 

  22. M. Murakawa, S. Yoshizawa, I. Kajitani, and T. Higuchi, “Evolvable hardware for generalized neural networks,” in Proc. Fifteenth Int. Joint Conf. Artif. Intell. (IJCAI-97), Morgan Kaufmann Publishers, 1997, pp. 1146—1151.

  23. M. A. Potter and K. A. De Jong, “Evolving neural networks with collaborative species,” in Proc. Summer Computer Simulation Conf., The Society for Computer Simulation, 1995.

  24. M. Salami, M. Iwata, and T. Higuchi, “Lossless image compression by evolvable hardware,” in Proc. 4th European Conf. Artif. Life (ECAL97), MIT Press, 1997, pp. 407—416.

  25. R. N. Scott and P. A. Parker, “;Myoelectric prostheses: State of the art,” J. Medical Engineering and Technology, vol. 12, no. 4, pp. 143—151, 1988.

    Google Scholar 

  26. M. Sipper, Evolution of Parallel Cellular Machines: The Cellular Programming Approach, volume 1194 of Lecture Notes in Computer Science, Springer-Verlag, 1997.

  27. M. Sipper, E. Sanchez, D. Mange, M. Tomassini, A. Perez-Uribe, and A. Stauffer, “A phylogenetic, ontogenetic, and epigenetic viewof bio-inspired hardware systems,” IEEE Trans. on Evolutionary Computation, vol. 1, no. 1, pp. 83—97, 1997.

    Google Scholar 

  28. M. Tanaka, H. Sakanashi, M. Salami, M. Iwata, T. Kurita, and T. Higuchi, “Data compression for digital color electrophotographic printer with evolvable hardware,” in Evolvable Systems: From Biology to Hardware. Second International Conference, ICES 98, volume 1478 of Lecture Notes in Computer Science, M. Sipper et al. (eds.), Springer-Verlag, 1998, pp. 106—114.

  29. A. Thompson, “An evolved circuit, intrinsic in silicon, entwined with physics,” in Evolvable Systems: From Biology to Hardware. First International Conference, ICES 96, volume 1259 of Lecture Notes in Computer Science, T. Higuchi et al. (eds.), Springer-Verlag, 1997, pp. 390—405.

  30. J. Torresen, “Evolvable hardware—A short introduction,” in Proc. Int. Conf. Neural Information Processing (ICONIP'.97, Dunedin, NewZealand), Springer-Verlag: Singapore, 1997, vol. 1, pp. 674—677.

    Google Scholar 

  31. J. Torresen, “A divide-and-conquer approach to evolvable hardware,” in Evolvable Systems: From Biology to Hardware. Second International Conference, ICES 98, volume 1478 of Lecture Notes in Computer Science, M. Sipper et al. (eds.), Springer-Verlag, 1998, pp. 57—65.

  32. J. Torresen, “Evolvable hardware—The coming hardware design method?” in Neuro-fuzzy techniques for Intelligent Information Systems, N. Kasabov and R. Kozma (eds.), Physica-Verlag (Springer-Verlag), 1999, pp. 435—449.

  33. J. Torresen, “Increased complexity evolution applied to evolvable hardware,” in Smart Engineering System Design: Neural Networks, Fuzzy Logic, Evolutionary Programming, Data Mining, and Complex Systems, Proc. of ANNIE'99, Dagli et al. (eds.), ASME Press, 1999, pp. 429—436.

  34. J. Torresen, “Possibilities and limitations of applying evolvable hardware to real-world application,” in Field-Programmable Logic and Applications: 10th International Conference on Field Programmable Logic and Applications (FPL-2000), volume 1896 of Lecture Notes in Computer Science, R. W. Hartenstein et al. (eds.), Springer-Verlag, 2000, pp. 230—239.

  35. J. Torresen, “Scalable evolvable hardware applied to road image recognition,” in Proc. of the 2nd NASA/DoD Workshop on Evolvable Hardware, J. Lohn et al. (eds.), IEEE Computer Society: Silicon Valley, 2000, pp. 245—252.

    Google Scholar 

  36. J. Torresen, “Two-step incremental evolution of a digital logic gate based prosthetic hand controller,” in Evolvable Systems: From Biology to Hardware. Fourth Int. Conf. (ICES'01), volume 2210 of Lecture Notes in Computer Science, Springer-Verlag, 2001, pp. 1—13.

    Google Scholar 

  37. J. Torresen, “Reconfigurable logic applied for designing adaptive hardware systems,” in Proc. Int. Conf. Advances in Infrastructure for e-Business, e-Education, e-Science, and e-Medicine on the Internet (SSGRR'2002W), Scuola Superiore G. Reiss Romoli, January 2002.

  38. J. Torresen and O. Landsverk, “A reviewof parallell implementations of backpropagation neural networks,” in Parallel Architectures for Artificial Neural Networks, N. Sundararajan and P. Saratchandran (eds.), IEEE CS Press, 1998, chap. 2, pp. 25—63.

  39. G. P. Wagner, “Adaptation and the modular design of organisms,” in Advances in Artificial Life. Third European Conf. Artificial Life Proceedings, J. J. Merelo, F. Moran, A. Moran and P. Chacon (eds.), Springer-Verlag, 1995, pp. 317—328.

  40. G. P. Wagner, “Homologues, natural kinds and the evolution of modularity,” American Zoologist, vol. 36, no. 1, pp. 36—43, 1996.

    Google Scholar 

  41. X. Yao and T. Higuchi, “Promises and challenges of evolvable hardware,” in Evolvable Systems: From Biology to Hardware. First Int. Conf., ICES 96, volume 1259 of Lecture Notes in Computer Science, T. Higuchi et al. (eds.), Springer-Verlag, 1997, pp. 55—78.

  42. X. Yao and Y. Liu, “Evolutionary artificial neural networks that learn and generalize well,” in Proc. IEEE Int. Conf. Neural Networks (ICNN'96), Washington DC, IEEE Press, 1996, pp. 159—164.

    Google Scholar 

  43. M. Yasunaga, T. Nakamura, I. Yoshihara, and J. H. Kim, “Genetic algorithm-based design methodology for pattern recognition hardware,” in Evolvable Systems: From Biology to Hardware. Third Int. Conf., ICES 2000, volume 1801 of Lecture Notes in Computer Science, J. Miller et al. (eds.), Springer-Verlag, 2000, pp. 264—273.

Download references

Author information

Authors and Affiliations

Authors

Rights and permissions

Reprints and permissions

About this article

Cite this article

Torresen, J. A Scalable Approach to Evolvable Hardware. Genetic Programming and Evolvable Machines 3, 259–282 (2002). https://doi.org/10.1023/A:1020163325179

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1023/A:1020163325179

Navigation