Training Feedforward Neural Networks: Convergence and Robustness Analysis

摘要

We develop a new algorithm for the learning of feedforward neural networks, by stating the learning process as a parameter estimation problem. We provide an analysis of its convegence and robustness properties. Two different versions of the algorithm are discussed, depending on the way in which the training set is explored during learning. The simulation results, for both classification and function approximation problems, confirm the effectiveness of the proposed algorithm and its advantages with respect to error back-propagation and extended Kalman filter-based learning.