Abstract
Catalytic networks are abstracted from chemistry, and have recently been used to study cooperation in molecular evolution. Here catalytic networks are regarded as a connectionist model with sigma-pi units in a recurrent dynamics. This paper partly presents previous work on the learning and generalisation in an association task. A particular type of architecture for catalytic networks is put forward here. The architecture of doubly-linked chains has been found to provide useful dynamics for association, while it allows for a range of different chain lengths. The chains can also branch, giving for example a tree structure. The nodes at the branching points perform logical AND or OR, depending on their connection parameters. An example is demonstrated where words are associated with letters, and each letter can have alternative (localist) representations. The main features of this model are the high sensitivity to single inputs and the two-way association. Possible extensions to using stochastic dynamics and distributed representations are discussed.
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
Bagley, R. J. & Farmer, J. D. (1992). Spontaneous Emergence of a Metabolism. In C. G. Langton, C. Taylor, J. D. Farmer & S. Rasmussen (Eds.) Artificial Life II. Santa Fe Institute Proceedings Vol. X, (pp. 93–140). Redwood City, CA: Addison-Wesley.
Calvin, W. H. (1996). The cerebral code. Cambridge, MA: MIT Press.
Dittrich, P. & Banzhaf, W. (1998). Self-Evolution in a Constructive Binary String System. Artificial Life 4(2), 203–220.
Eigen, M. (1971). Selforganization of Matter and the Evolution of Biological Macromolecules. Die Naturwissenschaften 58, 465–523.
Eigen, M. & Schuster, P. (1978). The Hypercycle. A Principle of Natural Self-Organization. Part B: The Abstract Hypercycle. Die Naturwissenschaften 65, 7–41.
Farmer, J. D., Kauffman, S. A. & Packard, N. H. (1986). Autocatalytic replication of polymers. Physica D 22, 50–67.
Hertz, J., Krogh, A. and Palmer, R. G. (1991). Introduction to the theory of neural computation. Redwood City, Addison-Wesley.
HÜning, H. (1998a). Learning Decompositional Structures in a Network of Max-II Units with Exponents as Connection Strengths. In L. Niklasson, M. Boden & T. Ziemke (Eds.) ICANN’98, Proceedings of the 8th International Conference on Artificial Neural Networks, Sk5vde, Sweden, 2–4 September 1998. London: Springer Verlag 1998.
HÜning, H. (l998b). An Approach to Learning in Autocatalytic Sets in Analogy to Neural Networks. Published on CD-ROM: I. Aedo-Cuevas, C. Bousono-Calzon, F. Diaz-de-Maria, A. R. Figueiras-Vidal, C. Martin-Pascual & A. Rodriguez-de-las-Heras (Eds.) Workshop Learning 98, Universidad Carlos III de Madrid, Getafe, Madrid, Spain, 16–18 September 1998.
HÜning, H. (2000). A search for multiple autocatalytic sets in artificial chemistries based on boolean networks. In: M. A. Bedau, J. S. McCaskill, N. H. Packard & S. Rasmussen (Eds.) Artificial Life VII: Proceedings of the seventh international conference on artificial life, Portland, OR, USA. Cambridge, MA: MIT Press.
McClelland, J. L. & Rumelhart, D. E. (1981). An interactive activation model of context effects in letter perception: Part 1. An account of basic findings. Psychological Review 88(5), 375–407.
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag London
About this paper
Cite this paper
Hüning, H. (2001). Borrowing Dynamics from Evolution: Association using Catalytic Network Models. In: French, R.M., Sougné, J.P. (eds) Connectionist Models of Learning, Development and Evolution. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-0281-6_24
Download citation
DOI: https://doi.org/10.1007/978-1-4471-0281-6_24
Publisher Name: Springer, London
Print ISBN: 978-1-85233-354-6
Online ISBN: 978-1-4471-0281-6
eBook Packages: Springer Book Archive