Balakrishnan, J (2000) Neural network learning dynamics in a path integral framework. In: European Physical Journal B, 15 (4). pp. 679-683.
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.
|Item Type:||Journal Article|
|Additional Information:||Copyright for this article belongs to Springer Verlag.|
|Keywords:||statistical physics;thermodynamics;nonlinear dynamical systems|
|Department/Centre:||Division of Electrical Sciences > High Voltage Engineering (merged with EE)|
|Date Deposited:||30 Sep 2004|
|Last Modified:||19 Sep 2010 04:15|
Actions (login required)