Skip to main content

EVOLVABLE HARDWARE Genetic Programming of a Darwin Machine

  • Conference paper
Artificial Neural Nets and Genetic Algorithms

Abstract

For the past three years, the author has been dreaming of the possibility of building machines which are capable of evolution, called “Darwin Machines”. As a result of several brain storming sessions with some colleagues in electrical engineering, the author now realizes that hardware devices are on the market today, which use “software configurable hardware” technologies that the author believes can be used to build Darwin Machines within a year or two. This paper suggests there are at least two approaches to be taken. The first approach uses “software configurable hardware” chips, e.g. FPGAs (Field Programmable Gate Arrays), HDPLDs (High Density Programmable Logic Devices), or possibly a new generation of chips based on the ideas that FPGAs etc embody. The second approach uses a special hardware device called a “hardware accelerator” which accelerates the simulation in software of digital hardware devices containing up to several hundred thousand gates. Darwin Machines will be essential if artificial nervous systems are to be evolved for biots (i.e. biological robots) which consist of thousands of evolved neural network modules (called GenNets). The evolution time of 1000-GenNet biots will need to be reduced by many orders of magnitude if they are to be built at all. It is for this reason that Darwin Machines may prove to be a breakthrough in biotic design. When molecular scale technologies come on line in the late 1990s, the Darwin Machine approach will probably be the only way to build self assembling, self testing molecular scale devices.

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

Access this chapter

Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 39.99
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 54.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  • [ALife III] “Proceedings of the 3rd International Artificial Life Conference”, Santa Fe, New Mexico, 15–19 June, 1992. To appear.

    Google Scholar 

  • [Beer 1990] “Intelligence as Adaptive Behavior: An Experiment in Computational Neuroethology”, Beer R.D., Academic Press, 1990.

    Google Scholar 

  • [Beer & Gallagher 1991] “Evolving Dynamical Neural Networks for Adapative Behavior”, Beer R.D. & Gallagher J.C., Technical Report 17, 1991, Dept. of Computer & Engineering Science, Case Western Reserve University, Cleveland, Ohio.

    Google Scholar 

  • [Broesch 1991] “Practical Programmable Circuits: A Guide to PLDs, State Machines, and Microcontrollers”, J.D. Broesch, Academic Press, 1991.

    Google Scholar 

  • [Brooks 1990] “Elephants Don’t Play Chess”, Brooks R.A., in Designing Autonomous Agents: Theory and Practice from Biology to Engineering and Back, ed. Maes P., MIT Press, 1990.

    Google Scholar 

  • [Brooks 1992] “Artificial Life and Real Robots”, Brooks R.A., in “Toward a Practice of Autonomous Systems: Proceedings of the First European Conference on Artificial Life”, eds. F.J. Varela and P. Bourgine, MIT Press, 1992.

    Google Scholar 

  • [Carter et al 1988] “Molecular Electronic Devices”, F.L. Carter, R.E. Siatkowski, H. Wohltjen eds. North Holland, 1988.

    Google Scholar 

  • [de Garis 1990a] “Genetic Programming: Modular Evolution for Darwin Machines”, Hugo de Garis, IJCNN-90-WASH-DC, (Int. Joint Conf. on Neural Networks), January 1990, Washington DC, USA.

    Google Scholar 

  • [de Garis 1990b] “Genetic Programming: Building Nanobrains with Genetically Programmed Neural Network Modules”, Hugo de Garis, IJCNN-90 SANDIEGO (Int.Joint Conf. on Neural Networks), June 1990, San Diego, California, USA.

    Google Scholar 

  • [de Garis 1990c] “Genetic Programming: Building Artificial Nervous Systems Using Genetically Programmed Neural Network Modules”, Hugo de Garis, in Porter B.W. & Mooney R.J. eds., Proc. 7th. Int. Conf. on Machine Learning, pp 132-139, Morgan Kaufmann, 1990.

    Google Scholar 

  • [de Garis 1990d] “Genetic Programming: Evolution of a Time Dependent Neural Network Module Which Teaches a Pair of Stick Legs to Walk”, Hugo de Garis, ECAI-90, (9th. European Conf. on Artificial Intelligence), August 1990, Stockholm, Sweden.

    Google Scholar 

  • [de Garis 1991a] “Genetic Programming: Artificial Nervous Systems, Artificial Embryos and Embryological Electronics”, Hugo de Garis, in “Parallel Problem Solving from Nature”, Lecture Notes in Computer Science 496, Springer Verlag, 1991.

    Google Scholar 

  • [de Garis 1991b] “LIZZY: The Genetic Programming of an Artificial Nervous System”, Hugo de Garis, ICANN91, Int.Conf. on Artificial Neural Networks, June 1991, Espoo, Finland.

    Google Scholar 

  • [de Garis 1991c] “GenNETS: Genetically Programmed Neural Nets: Using the Genetic Algorithm to Train Neural Nets Whose Inputs and/or Outputs Vary in Time”, Hugo de Garis, IJCNN91 Singapore, Int.Joint Conf.on Neural Networks, November 1991, Singapore.

    Google Scholar 

  • [de Garis 1991d] “Genetic Programming”, Hugo de Garis, Ch. 8 in book “Neural and Intelligent Systems Integration”, ed. Branko Soucek, WILEY, 1991.

    Google Scholar 

  • [de Garis 1992a] “Steerable GenNETS: The Genetic Programming of Controllable Behaviors in GenNets”, Hugo de Garis, ECAL91 Paris, Proceedings of the 1st. European Conference on Artificial Life, MIT Press.

    Google Scholar 

  • [de Garis 1992b] “Artificial Embryology: The Genetic Programming of an Artificial Embryo”, Hugo de Garis, Ch. 14 in book “Dynamic, Genetic, and Chaotic Programming”, ed. Branko Soucek and the IRIS Group, WILEY, 1992.

    Google Scholar 

  • [de Garis 1992c] “Genetic Programming: Evolutionary Approaches to Multistrategy Learning”, Hugo de Garis, chapter 21 in “Machine Learning: A Multistrategy Approach, Vol. 4”, R.S. Michalski & G. Tecuci (Eds.), Morgan Kauffman, 1992.

    Google Scholar 

  • [de Garis 1993] “Genetic Programming: GenNets, Artificial Nervous Systems, Artificial Embryos”, Hugo de Garis, WILEY manuscript.

    Google Scholar 

  • [Drexler 1992] “Nanosystems: Molecular Machinery, Manufacturing and Computation”, Drexler K.E., Wiley, 1992.

    Google Scholar 

  • [Ecal91] “Toward a Practice of Autonomous Systems: Proceedings of the First European Conference on Artificial Life”, eds. F.J. Varela and P. Bourgine, MIT Press, 1992.

    Google Scholar 

  • [GA 1989] “Proceedings of the Third International Conference on Genetic Algorithms”, J.D. Schaffer ed., Morgan Kaufmann, 1989.

    Google Scholar 

  • [GA 1991] “Proceedings of the Fourth International Conference on Genetic Algorithms”, R.K. Belew and L.B. Booker eds., Morgan Kaufmann, 1991.

    Google Scholar 

  • [Goldberg 1989] “Genetic Algorithms in Search, Optimization, and Machine Learning”, D.E. Goldberg, Addison-Wesley, 1989.

    MATH  Google Scholar 

  • [Higuchi et al 1993] “Evolving Hardware with Genetic Learning: A First Step Towards Building a Darwin Machine”, T. Higuchi, T. Niwa, T. Tanaka, H. Iba, H. de Garis, T. Furuya, in “Proceedings of the 2nd Int. Conf. on the Simulation of Adaptive Behavior (SAB92), MIT Press, 1993.

    Google Scholar 

  • [Koza 1990] “Genetic Programming: A Paradigm for Genetically Breeding Populations of Computer Programs to Solve Problems”, Koza J. R., Stanford University Comp. Sci. Dept. Technical Report, STAN-CS-90-1314, June 1990.

    Google Scholar 

  • [Koza 1992a] “Genetic Programming Paradigm: Genetically Breeding Populations of Computer Programs to Solve Problems”, Koza J. R., Ch. 10 in “Dynamic, Genetic and Chaotic Programming”, ed. Branko Soucek and the IRIS Group, WILEY 1992.

    Google Scholar 

  • [Koza 1992b] “Genetic Programming”: On the Programming of Computers by Means of Natural Selection”, Koza J. R., MIT Press.

    Google Scholar 

  • [Lattice 1992] “pLSI and ispLSI Data Book and Handbook”, Lattice Corporation, Hillsboro, Oregon, 1992.

    Google Scholar 

  • [Lattice 1992] “GAL Data Book”, Lattice Corporation, Hillsboro, Oregon, 1992.

    Google Scholar 

  • [Ning et al 1991] “SEAS: A Simulated Evolution Approach for Analog Circuit Synthesis”, Zhen-Qiu Ning, Ton Mouthaan, and Hans Wallinga, in Proceedings of CICC, IEEE, 1991.

    Google Scholar 

  • [PPSN91] “Parallel Problem Solving from Nature”, Lecture Notes in Computer Science, No. 496, Schwefel H.-P. and Manner R. eds., Springer Verlag, 1991.

    Google Scholar 

  • [Schneiker 1989] “Nano Technology with Feynman Machines: Scanning Tunneling Engineering and Artificial Life”, Schneiker C., in “Artificial Life”, Langton C.G. ed., Addison Wesley, 1989.

    Google Scholar 

  • [Xilinx 1991] “The Programmable Gate Array Data Book”, Xilinx Corporation, San Jose, CA, 1991.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

Editors and Affiliations

Rights and permissions

Reprints and permissions

Copyright information

© 1993 Springer-Verlag/Wien

About this paper

Cite this paper

de Garis, H. (1993). EVOLVABLE HARDWARE Genetic Programming of a Darwin Machine. In: Albrecht, R.F., Reeves, C.R., Steele, N.C. (eds) Artificial Neural Nets and Genetic Algorithms. Springer, Vienna. https://doi.org/10.1007/978-3-7091-7533-0_64

Download citation

  • DOI: https://doi.org/10.1007/978-3-7091-7533-0_64

  • Publisher Name: Springer, Vienna

  • Print ISBN: 978-3-211-82459-7

  • Online ISBN: 978-3-7091-7533-0

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics