Abstract
We experimentally show that computing with attractors leads to fast adaptive behavior in which dynamical associations can be made between different inputs which initially produce sharply distinct outputs. We do so by first defining a set of simple local procedures which allow a computing array to change its state in time so as to produce classical Pavlovian conditioning. We then examine the dynamics of coalescence and dissociation of attractors with a number of quantitative experiments. We also show how such arrays exhibit generalization and differentiation of inputs in their behavior.
Similar content being viewed by others
References
J. S. Albus,Brains, Behavior, and Robotics (Byte/McGraw-Hill, Petersborough, New Hampshire, 1981), and references therein.
G. M. Edelman and V. B. Mountcastle, inThe Mindful Brain (MIT Press, Cambridge, Massachusetts, 1978).
J. von Neumann, inTheory of Self-Reproducing Automata, A. W. Burks, ed. (University of Illinois Press, Urbana, Illinois, 1966).
B. A. Huberman and T. Hogg,Phys. Rev. Lett. 52:1048 (1984); T. Hogg and B. A. Huberman,Proc. Natl. Acad. Sci. (USA) 81:6871 (1984).
I. P. Pavlov,Conditioned Reflexes (Dover, New York 1960).
E. R. Hilgard and G. H. Bower,Theories of Learning, 3rd ed. (Meredith Publishing Co., New York, 1966), Chap. 3.
G. M. Edelman and L. Finkel, inDynamic Aspects of Neocortical Function, G. M. Edelman, W. M. Cowan, and W. E. Gall, eds. (Wiley, New York, 1984).
B. Julesz,Nature (Londen) 290:91 (1981).
D. R. Reddy, ed.,Speech Recognition: Papers Presented at the 1974 IEEE Symposium (Academic Press, New York, 1975); G. R. Doddington and T. B. Schalk,IEEE Spectrum 18:9 (1981).
M. Minsky and S. Papert,Perceptrons: An Introduction to Computational Geometry (MIT Press, Cambridge, Massachusetts, 1969);
W. A. Little,Math. Biol. 19:101 (1974) and G. E. Hinton, T. J. Sejnowsky, and D. Ackley, CMU-CS-84-119 Technical Report (1984).
T. Hogg and B. A. Huberman, Attractors on finite sets: The dissipative dynamics of computing structures,Phys. Rev. A (October 1985), to appear.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Hogg, T., Huberman, B.A. Parallel computing structures capable of flexible associations and recognition of fuzzy inputs. J Stat Phys 41, 115–123 (1985). https://doi.org/10.1007/BF01020606
Received:
Revised:
Issue Date:
DOI: https://doi.org/10.1007/BF01020606