Adaptive Method of Realizing Natural Gradient Learning for Multilayer Perceptrons

摘要

The natural gradient learning method is known to have ideal perfor- mances for on-line training of multilayer perceptrons. It avoids plateaus, which give rise to slow convergence of the backpropagation method. It is Fisher efficient, whereas the conventional method is not. However, for im- Plementing the method, it is necessary to calculate the Fisher information Matrix and its inverse, which is practically very difficult.