Abstract
A review is given of approaches to growing neural networks and electronic circuits. A new method for growing graphs and circuits using a developmental process is discussed. The method is inspired by the view that the cell is the basic unit of biology. Programs that construct circuits are evolved to build a sequence of digital circuits at user specified iterations. The programs can be run for an arbitrary number of iterations so circuits of huge size could be created that could not be evolved. It is shown that the circuit building programs are capable of correctly predicting the next circuit in a sequence of larger even parity functions. The new method however finds building specific circuits more difficult than a non-developmental method.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Astor J. C., and Adami C. (2000), “A Development Model for the Evolution of Artificial Neural Networks”, Artificial Life, Vol. 6, pp. 189–218.
Bentley P., and Kumar S. (1999), “Three ways to grow designs: A comparison of embryogenies for an Evolutionary Design Problem”, in Proceedings of the Congress on Evolutionary Computation, IEEE Press, pp. 35–43.
Boers, E. J. W., and Kuiper, H. (1992), “Biological metaphors and the design of modular neural networks”, Masters thesis, Department of Computer Science and Department of Experimental and Theoretical Psychology, Leiden University.
Bongard J. C. and Pfeifer R. (2001), “Repeated Structure and Dissociation of Genotypic and Phenotypic Complexity in Artificial Ontogeny”, in Spector L. et al. (eds.) Proceedings of the Genetic and Evolutionary Computation Conference, Morgan-Kaufmann, pp. 829–836.
Cangelosi, A., Parisi, D., and Nolfi, S. (1993), “Cell Division and Migration in a ‘Genotype’ for Neural Networks”, Technical report PCIA-93, Institute of Psychology, CNR, Rome.
Dellaert, F. (1995), “Toward a Biologically Defensible Model of Development”, Masters thesis, Department of Computer Engineering and Science, Case Western Reserve University.
Edwards R. T (2003), “Circuit Morphologies and Ontogenies”, in NASA/DOD Conference on Evolvable Hardware, IEEE Computer Society, pp. 251–260.
Eggenberger P. (1997), “Evolving morphologies of simulated 3D organisms based on differential gene expression”, in Proceedings of 4th European Conference on Artificial Life, pp. 205–213.
Gordon T., and Bentley P. J. (2003) “Towards Development in Evolvable Hardware”, in NASA/DOD Conference on Evolvable Hardware, IEEE Computer Society, pp. 241–250.
Gruau, F. (1994), “Neural Network Synthesis using Cellular Encoding and the Genetic Algorithm”, PhD thesis, Ecole Normale Supérieure de Lyon.
Gruau, F., Whitley, D., and Pyeatt, L. (1996) “A Comparison between Cellular Encoding and Direct Encoding for Genetic Neural Networks”, in Proceedings of the 1st Annual Conference on Genetic Programming, Stanford.
Hemmi H., Mizoguchi, J., and Shimohara K. (1994), “Development and Evolution of Hardware Behaviors”, in Proceedings of Artificial Life IV, pp. 371–376.
Haddow, P. C., Tufte G., and van Remortel P. (2001) “Shrinking the genotype: L-systems for evolvable hardware”, in 4th International Conference on Evolvable Systems: From Biology to Hardware, Lecture Notes in Computer Science, Vol. 2210, Springer-Verlag, pp. 128–139.
Hornby G. S., and Pollack J. B. (2001), “The Advantages of Generative Grammatical Encodings for Physical Design”, in Proceedings of the Congress on Evolutionary Computation, IEEE Press, pp. 600–607.
Huelsbergen L. (1998), “Finding general Solutions to the Parity Problem bu Evolving Machine-Language Representations”, in Proc. Conf. on Genetic Programming, pp. 158–166.
Jacobi, N. (1995), “Harnessing Morphogenesis”, Cognitive Science Research Paper 423, COGS, University of Sussex.
Kitano, H. (1990), “Designing neural networks using genetic algorithms with graph generation system”, Complex Systems, Vol. 4, pp. 461–476.
Kodjabachian, J. and Meyer, J-A. (1998), “Evolution and Development of Neural Controllers for Locomotion, Gradient-Following and Obstacle-Avoidance in Artificial Insects”, IEEE Transactions on Neural Networks, Vol. 9, pp. 796–812.
Koza, J., Bennett III, F. H., Andre, D., and Keane, M. A. (1999). Genetic Programming III. Darwinian Invention and Problem Solving. Morgan Kaufmann.
Lindenmeyer, A. (1968), “Mathematical models for cellular interaction in development, parts I and II”, Journal of Theoretical Biology, Vol. 18, pp. 280–315.
Miller, J. F. and Thomson, P. (2000), “Cartesian genetic programming”, in Proceedings of the 3rd European Conference on Genetic Programming. LNCS, Vol. 1802, pp.121–132.
Nolfi, S., and Parisi, D. (1991) “Growing neural networks”, Technical report PCIA-91-15, Institute of Psychology, CNR, Rome.
Siddiqi, A. A., and Lucas S. M. (1998), “A comparison of matrix rewriting versus direct encoding for evolving neural networks”, in Proceedings of the 1998 IEEE International Conference on Evolutionary Computation, IEEE Press, pp. 392–397.
Sims K. (1994), “Evolving 3D morphology and behaviour by competition”, in Proceedings of Artificial Life IV, pp. 28–39.
Vassilev V. K., and Miller J. F. (2000), “The Advantages of Landscape Neutrality in Digital Circuit Evolution”, 3rd International Conference on Evolvable Systems: From Biology to Hardware, Lecture Notes in Computer Science, Vol. 1801, Springer-Verlag, pp. 252–263.
Vassilev V. K. and Miller J. F., (2000), “Scalability Problems of Digital Circuit Evolution”, in Proceedings of the 2nd NASA/DOD Workshop on Evolvable Hardware, IEEE Computer Society, pp. 55–64
Wong M. L., and Leung K. S. (1996), “Evolving Recursive Functions for the Even-Parity Problem Using Genetic Programming”, in Advances in GP, MIT Press, Vol. 2, pp. 221–240.
Yu, T. (1999), “An analysis of the Impact of Functional Programming Techniques on Genetic Programming, Ph. D. Thesis, University College London, UK.
Yu, T. and Miller, J. (2001), “Neutrality and the evolvability of Boolean function landscape”, in Proceedings of the 4th European Conference on Genetic Programming, Springer-Verlag, pp. 204–217.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Miller, J.F., Thomson, P. (2003). A Developmental Method for Growing Graphs and Circuits. In: Tyrrell, A.M., Haddow, P.C., Torresen, J. (eds) Evolvable Systems: From Biology to Hardware. ICES 2003. Lecture Notes in Computer Science, vol 2606. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-36553-2_9
Download citation
DOI: https://doi.org/10.1007/3-540-36553-2_9
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-00730-2
Online ISBN: 978-3-540-36553-2
eBook Packages: Springer Book Archive