Abstract:
A path-integral formalism is proposed for studying the dynamical evolution in time of patterns in an artificial neural network in the presence of noise. An effective cost function is constructed which determines the unique global minimum of the neural network system. The perturbative method discussed also provides a way for determining the storage capacity of the network.
Similar content being viewed by others
Author information
Authors and Affiliations
Additional information
Received 19 November 1999
Rights and permissions
About this article
Cite this article
Balakrishnan, J. Neural network learning dynamics in a path integral framework. Eur. Phys. J. B 15, 679–683 (2000). https://doi.org/10.1007/s100510051172
Issue Date:
DOI: https://doi.org/10.1007/s100510051172