Stability of Back Propagation Training Algorithm for Neural Networks
Abstract
In this paper, we derive and prove the stability bounds of the momentum coefficient µ and the learning rate η of the back propagation updating rule in Artificial Neural Networks .The theoretical upper bound of learning rate η is derived and its practical approximation is obtained
Keywords
Key words : BP training algorithm, Ann, Gradient Descent Training Algorithm, Gradient Descent with Momentum and Lyapunov Stability .Metrics