Abstract
The notion of conceptual structure in CA rules that perform the density classification task (DCT) was introduced by [1]. Here we investigate the role of process-symmetry in CAs that solve the DCT, in particular the idea of conceptual similarity, which defines a novel search space for CA rules. We report on two new process-symmetric one-dimensional rules for the DCT which have the highest “balanced” performance observed to date on this task, as well as the highest-performing CA known to perform the DCT in two dimensions. Finally, we investigate the more general problem of assessing how different learning strategies (based on evolution and coevolution, with and without spatial distribution), previously compared by [2], are suited to exploit conceptual structure in learning CAs to perform collective computation.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Marques-Pita, M., Manurung, R., Pain, H.: Conceptual representations: What do they have to say about the density classification task by cellular automata? In: Jost, J., Reed-Tsotchas, F., Schuster, P. (eds.) ECCS 2006. European Conference on Complex Systems (2006)
Mitchell, M., Thomure, M.D., Williams, N.L.: The role of space in the success of coevolutionary learning. In: Proceedings of Artificial Life X: Tenth Annual Conference on the Simulation and Synthesis of Living Systems (2006)
Zhirnov, V., Cavin, R., Lemming, G., Galatsis, K.: An assessment of integrated digital cellular automata architectures. Computer 41(1), 38–44 (2008)
Mitchell, M., Crutchfield, J., Hraber, P.: Revisiting the edge of chaos: Evolving cellular automata to perform computations. Complex Systems 7, 89–130 (1993)
Gacs, P., Kurdyumov, L., Levin, L.: One-dimensional uniform arrays that wash out finite islands. Probl. Peredachi. Inform. 14, 92–98 (1978)
Gonzaga de Sá, P., Maes, C.: Gacs-Kurdyumov-Levin automaton revisited. Journal of Statistical Physics 67(3-4), 507–522 (1992)
Andre, D., Bennett III, F., Koza, J.: Discovery by genetic programming of a cellular automata rule that is better than any known rule for the majority classification problem. In: Koza, J., Goldberg, D., Fogel, D. (eds.) Proceedings of the First Annual Conference on Genetic Programming, pp. 3–11. MIT Press, Cambridge (1996)
Das, R., Mitchell, M., Crutchfield, J.: A genetic algorithm discovers particle-based computation in cellular automata. In: Davidor, Y., Schwefel, H.P., Männer, R. (eds.) Proceedings of the Int.Conf. on Evolutionary Computation, pp. 344–353 (1994)
Juillé, H., Pollack, B.: Coevolving the ideal trainer: Application to discovery of cellular automata rules. In: Garzon, M.H., Goldberg, D.E., Iba, H., Riolo, R. (eds.) Genetic Programming 1998: Proceedings of the Third Annual Conference. Morgan Kaufmann, San Francisco (1998)
Ferreira, C.: Gene expression programming: A new adapive algorithm for solving problems. Complex Systems 13(2), 87–129 (2001)
Karmiloff-Smith, A.: Beyond Modularity: A Developmental Perspective on Cognitive Science. MIT Press, Cambridge (1992)
Gärdenfors, P.: Conceptual Spaces: The Geometry of Tought. MIT Press/Bradford Books (2000)
Marques-Pita, M.: Aitana: A Developmental Cognitive Artifact to Explore the Evolution of Conceptual Representations of Cellular Automata-based Complex Systems. PhD thesis, School of Informatics, University of Edinburgh, Edinburgh, UK (2006)
Holland, J., Holyoak, K., Nisbett, R., Thagard, P.: Induction: Processes of Inference, Learning and Discovery. MIT Press, Cambridge (1986)
Piaget, J.: The Origins of Intelligence in Children. International University Press (1952)
Piaget, J.: The Child’s Construction of Reality. Routledge and Kegan Paul (1955)
Marques-Pita, M., Rocha, L.M.: Conceptual structure in cellular automata: The density classification task. In: Bullock, S., Noble, J., Watson, R.A., Bedau, M.A. (eds.) Proceedings of the Eleventh International Conference on Artificial Life (Alife XI). MIT Press, Cambridge (2008)
Crutchfield, J.P., Mitchell, M., Das, R.: The evolutionary design of collective computation in cellular automata. In: Crutchfield, J.P., Schuster, P.K. (eds.) Evolutionary Dynamics—Exploring the Interplay of Selection, Neutrality, Accident, and Function, pp. 361–411. Oxford University Press, New York (2003)
Woltz, D., De Oliveira, P.: Very effective evolutionary techniques for searching cellular automata rule spaces. Journal of Cellular Automata (to appear)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Marques-Pita, M., Mitchell, M., Rocha, L.M. (2008). The Role of Conceptual Structure in Designing Cellular Automata to Perform Collective Computation. In: Calude, C.S., Costa, J.F., Freund, R., Oswald, M., Rozenberg, G. (eds) Unconventional Computing. UC 2008. Lecture Notes in Computer Science, vol 5204. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-85194-3_13
Download citation
DOI: https://doi.org/10.1007/978-3-540-85194-3_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-85193-6
Online ISBN: 978-3-540-85194-3
eBook Packages: Computer ScienceComputer Science (R0)