Title :
Optimal convergence of on-line backpropagation
Author :
Gori, Marco ; Maggini, Marco
Author_Institution :
Dept. of Syst. & Inf., Firenze Univ., Italy
fDate :
1/1/1996 12:00:00 AM
Abstract :
Many researchers are quite skeptical about the actual behavior of neural network learning algorithms like backpropagation. One of the major problems is with the lack of clear theoretical results on optimal convergence, particularly for pattern mode algorithms. In this paper, we prove the companion of Rosenblatt´s PC (perceptron convergence) theorem for feedforward networks (1960), stating that pattern mode backpropagation converges to an optimal solution for linearly separable patterns
Keywords :
backpropagation; convergence; feedforward neural nets; optimisation; perceptrons; feedforward networks; linearly separable patterns; neural network learning algorithms; online backpropagation; optimal convergence; pattern mode backpropagation; perceptron convergence theorem; Backpropagation algorithms; Computer networks; Convergence; Cost function; Equations; Neural networks; Neurons; Pattern analysis; Shape;
Journal_Title :
Neural Networks, IEEE Transactions on
