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.
CITATION STYLE
Balakrishnan, J. (2000). Neural network learning dynamics in a path integral framework. European Physical Journal B, 15(4), 679–683. https://doi.org/10.1007/s100510051172
Mendeley helps you to discover research relevant for your work.