Neural network learning dynamics in a path integral framework
Department of High Voltage Engineering, Indian Institute of Science,
Bangalore, 560 012, India
Published online: 15 June 2000
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.
PACS: 02.90.+p – Other topics in mathematical methods in physics / 05.90.+m – Other topics in statistical physics, thermodynamics, and nonlinear dynamical systems / 87.10.+e – General theory and mathematical aspects
© EDP Sciences, Società Italiana di Fisica, Springer-Verlag, 2000