Abstract
In this chapter we will describe a developmental form of Cartesian Genetic Programming (CGP) known as a CGP Developmental Network (CGPDN). The CGPDN is a kind of constructivist artificial neural network in which the neuron is represented by seven evolved CGP programs. These programs are each responsible for some neuro-inspired aspect of the artificial neuron (i.e. soma, dendrites, axons, synapses and neurite branches). The network is usually initialized with a few neurons. However, when the evolved programs are executed the network can develop into a network of arbitrary complexity while simultaneously solving a computational problem. We have tested this model on two well known problem in artificial intelligence: Wumpus World and Checkers (Draughts). The role of CGP is to evolve programs that encode the capability of learning, rather than learned information directly. All specific learned information is acquired post-evolution while solving problems.
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
Alberts, B.: Molecular Biology of the Cell, 3 edn. Garland Science (2002)
Belew, R.K.: Interposing an Ontogenetic Model Between Genetic Algorithms and Neural Networks. Advances in Neural Information Processing Systems (NIPS) pp. 99–106 (1992)
Chalup, S.K.: Issues of Neurodevelopment in Biological and Artificial Neural Networks. Proc. Biannual Conference on Artificial Neural Networks and Expert Systems pp. 40–45 (2001)
Chen, X., Hurst, S.L.: A Comparison of Universal-Logic-Module Realizations and Their Application in the Synthesis of Combinatorial and Sequential Logic Networks. IEEE Transactions on Computers 31, 140–147 (1982)
Dawkins, R., Krebs, J.R.: Arms races between and within Species. In: Proc. Royal Society of London Series B, vol. 205, pp. 489–511 (1979)
Dellaert, F., Beer, R.D.: Toward an evolvable model of development for autonomous agent synthesis. In: R. Brooks, P. Maes (eds.) Artificial Life IV: Proceedings of the Fourth International Workshop on the Synthesis and Simulation of Living Systems. MIT Press (1994)
Fogel, D.B.: Blondie24: Playing at the Edge of AI. Morgan Kaufmann (2002)
Graham, B.: Multiple Forms of Activity-Dependent Plasticity Enhance Information Transfer at a Dynamic Synapse. In: J.R. Dorronsoro (ed.) Proc. International Conference on Artificial Neural Networks, LNCS, vol. 2415, pp. 45–50. Springer (2002)
Gruau, F.: Genetic Synthesis of Modular Neural Networks. In: Proc. International Conference on Genetic Algorithms, pp. 318–325 (1993)
Hillis, W.: Co-evolving parasites improve simulated evolution as an optimization procedure. Physica D 42, 228–234 (1990)
Irving, G., Donkers, J., Uiterwijk, J.: Solving Kalah. International Computer Games Association Journal 23(3), 139–147 (2000)
Kandel, E.R., Schwartz, J.H., Jessell, T.M. (eds.): Principles of Neural Science, 4 edn. McGraw-Hill (2000)
Kendall, G., Whitwell, G.: An Evolutionary Approach for the Tuning of a Chess Evaluation Function using Population Dynamics. In: Proc. IEEE Congress on Evolutionary Computation, pp. 995–1002 (2001)
Khan, G.M., Miller, J.F., Halliday, D.M.: Coevolution of Intelligent Agents using Cartesian Genetic Programming. In: Proc. Genetic and evolutionary Computation Conference, pp. 269–276 (2007)
Khan, G.M., Miller, J.F., Halliday, D.M.: Coevolution of Neuro-developmental Programs That Play Checkers. Proc. International Conference on Evolvable Systems 5216, 352–362 (2008)
Khan, G.M., Miller, J.F., Halliday, D.M.: In Search of Intelligent Genes: The Cartesian Genetic Programming Computational Neuron (CGPCN). In: Proc. IEEE Congress on Evolutionary Computation, pp. 574–581. IEEE Press (2009)
Khan, G.M., Miller, J.F., Halliday, D.M.: Evolution of Cartesian Genetic Programs for Development of Learning Neural Architecture. Evolutionary Computation 19(3) (2011). In press
Kitano, H.: Designing neural networks using genetic algorithms with graph generation system. Complex Systems 4, 461–476 (1990)
Koza, J.R.: Genetic Programming: On the Programming of Computers by Means of Natural Selection. MIT Press (1992)
Kuffler, S.W., Nichols, J.G., Martin, A.R.: From Neuron to Brain, A Cellular Approach to the Function of the Nervous System, 2 edn. Sinauer Press (1984)
Lubberts, A., Miikkulainen, R.: Co-Evolving a Go-Playing Neural Network. In: Coevolution: Turning Adaptive Algorithms upon Themselves, Birds-of-a-Feather Workshop, Genetic and Evolutionary Computation Conference, p. 6 (2001)
McCloskey, M., Cohen, N.J.: Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem. The Psychology of Learning and Motivation 24, 109–165 (1989)
Miller, J.F.: Evolving Developmental Programs for Adaptation, Morphogenesis and Self-Repair. In: Proc. European Conference on Advances in Artificial Life, LNAI, vol. 2801, pp. 289–298 (2003)
Miller, J.F.: Evolving a self-repairing, self-regulating, French flag organism. In: Proc. Genetic and Evolutionary Computation Conference, vol. 3102, pp. 129–139 (2004)
Miller, J.F., Khan, G.M.: Where is the Brain inside the Brain? On Why Artificial Neural Networks should be Developmental. Memetic Computing 3(3), YY–YY (2011). In press
Miller, J.F., Thomson, P.: Cartesian Genetic Programming. In: Proc. European Conference on Genetic Programming, LNCS, vol. 1802, pp. 121–132 (2000)
Miller, J.F., Vassilev, V.K., Job, D.: Principles in the Evolutionary Design of Digital Circuits – Part I. Genetic Programming and Evolvable Machines 1, 7–35 (2000)
Moriarty, D., Miikkulainen, R.: Discovering Complex Othello Strategies Through Evolutionary Neural Networks. Connection Science 7, 195–209 (1995)
Nolfi, S., Floreano, D.: Co-Evolving predator and prey robots: Do ‘arms races’ arise in artificial evolution? Artificial Life 4, 311–335 (1998)
Panchev, C., Wermter, S., Chen, H.: Spike-Timing Dependent Competitive Learning of Integrate-and-Fire Neurons with Active Dendrites. In: J.R. Dorronsoro (ed.) Proc. International Conference on Artificial Neural Networks, LNCS, vol. 2415, pp. 896–901. Springer (2002)
Paredis, J.: Coevolutionary Computation. Artificial Life 2(4), 355–375 (1995)
Ratcliff, R.: Connectionist Models of Recognition and Memory: Constraints Imposed by Learning and Forgetting Functions. Psychological Review 97, 205–308 (1990)
Rosin, C.D., Belew, R.K.: New Methods for Competitive Evolution. Evolutionary Computation 5, 1–29 (1997)
Russell, S., Norvig, P.: Artificial Intelligence: A Modern Approach. Prentice Hall (1995)
Shepherd, G.M.: The Synaptic Organization of the Brain. Oxford University Press (1990)
Spector, L.: Simultaneous Evolution of Programs and their Control Structures. In: P.J. Angeline, J.K.E. Kinnear (eds.) Advances in Genetic Programming 2, pp. 137–154. MIT Press (1996)
Spector, L., Luke, S.: Cultural Transmission of Information in Genetic Programming. In: J.R. Koza, D.E. Goldberg, D.B. Fogel, R.L. Riolo (eds.) Proc. Conference on Genetic Programming, pp. 209–214. MIT Press (1996)
Stanley, K., Miikkulainen, R.: Competitive coevolution through evolutionary complexification. Journal of Artificial Intelligence Research 21, 63–100 (2004)
Stanley, K.O., Miikkulainen, R.: Evolving Neural Networks Through Augmenting Topologies. Evolutionary Computation 10(2), 99–127 (2002)
Van Valin, L.: A new evolutionary law. Evolution Theory 1, 1–30 (1973)
Wee-Chong, O., Yew-Jin, L.: An Investigation on Piece Differential Information in Co-Evolution on Games using Kalah. In: Proc. Congress on Evolutionary Computation, pp. 1632–1638. IEEE Press (2003)
Yob, G.: Hunt the Wumpus. Creative Computing, pp. 51–54 (1975)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Khan, G.M., Miller, J.F. (2011). The CGP Developmental Network. In: Miller, J. (eds) Cartesian Genetic Programming. Natural Computing Series. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-17310-3_9
Download citation
DOI: https://doi.org/10.1007/978-3-642-17310-3_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-17309-7
Online ISBN: 978-3-642-17310-3
eBook Packages: Computer ScienceComputer Science (R0)