Abstract
We study the dynamical behavior of complex adaptive automata during unsupervised learning of periodic training sets. A new technique for their analysis is presented and applied to an adaptive network with distributed memory. We show that with general imput pattern sequences, the system can display behavior that ranges from convergence into simple fixed points and oscillations to chaotic wanderings. We also test the ability of the self-organized automaton to recognize spatial patterns, discriminate between them, and to elicit meaningful information out of noisy inputs. In this configuration we determine that the higher the ratio of excitation to inhibition, the broader the equivalence class into which patterns are put together.
Similar content being viewed by others
References
J. A. Feldman and D. H. Ballard,Cognitive Science 6:205 (1982) and references therein.
T. Kohonen,Associative Memory (Springer, New York, 1978); see alsoParallel Models of Associative Memory, E. E. Hinton and J. A. Anderson, eds. (L. Elbaum Associates, Hillsdale, New Jersey, 1981).
G. Edelman and B. Mountcastle,The Mindful Brain (MIT Press, Boston, 1978); W. J. Freeman, inSynergetics of the Brain, H. Haken, ed. (Springer, New York, 1983).
V. I. Arnold,Mathematical Methods of Classical Mechanics (Springer, New York, 1978).
F. Rosenblatt,Principles of Neurodynamics (Spartan Books, Washington, D.C., 1962); M. Minsky and S. Papert,Perceptrons (MIT Press, Cambridge, 1969).
J. S. Koford and G. F. Groner,IEEE Trans. Information Theory 12:42 (1966).
K. Fukushima,Systems Computer Controls 6:15 (1975);Tech. Monograph (N.H.K) 30:178 (1981).
M. Osborne,IEEE Trans. Comp. C-26:1302 (1977).
I. Morishita and H. Yajima,Kybernetik 11:154 (1972).
R. Takiyama,Pattern Recognition 15:405 (1982).
J. P. Crutchfield, D. Farmer, and B. A. Huberman,Phys. Rep. 92:45 (1982).
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
d'Humières, D., Huberman, B.A. Dynamics of self-organization in complex adaptive networks. J Stat Phys 34, 361–379 (1984). https://doi.org/10.1007/BF01018550
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF01018550