A successive overrelaxation backpropagation algorithm for neural-network training

Authors:
R. De Leone;R. Capparuccia;E. Merelli
Affiliations:
Dipartimento di Matematica e Fisica, Camerino Univ., Macerata;-;-
Venue:
IEEE Transactions on Neural Networks
Year:
1998

Citing 0
Cited 2

A new fuzzy neural network with fast learning algorithm and guaranteed stability for manufacturing process control

Fuzzy Sets and Systems - Fuzzy systems
Learning Capability: Classical RBF Network vs. SVM with Gaussian Kernel

IEA/AIE '02 Proceedings of the 15th international conference on Industrial and engineering applications of artificial intelligence and expert systems: developments in applied artificial intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

A variation of the classical backpropagation algorithm for neural network training is proposed, and convergence is established using the perturbation results of Mangasarian and Solodov (1994). The algorithm is similar to the successive overrelaxation (SOR) algorithm for systems of linear equations and linear complementary problems in using the most recently computed values of the weights to update the values on the remaining arcs