Title :
A complement to the back-propagation algorithm: an upper bound for the learning rate
Author :
Cerqueira, Jés J F ; Palhares, Álvaro G B ; Madrid, Marconi K.
Author_Institution :
Univ. Estadual de Campinas, Sao Paulo, Brazil
Abstract :
This paper presents as complement for the back-propagation algorithm, a local convergence analysis derived from a vectorial approach. The analysis is made through application of Lyapunov´s second method, and it supplies an upper bound for the learning rate
Keywords :
backpropagation; multilayer perceptrons; Lyapunov´s second method; back-propagation algorithm; learning rate; local convergence analysis; vectorial approach; Algorithm design and analysis; Artificial neural networks; Convergence; Education; Multi-layer neural network; Multilayer perceptrons; Optimization methods; RNA; Upper bound; Vectors;
Conference_Titel :
Neural Networks, 2000. IJCNN 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on
Conference_Location :
Como
Print_ISBN :
0-7695-0619-4
DOI :
10.1109/IJCNN.2000.860823
