Title :
A backpropagation learning framework for feedforward neural networks
Author :
Yu, Xinghuo ; Efe, M Onder ; Kaynak, Okyay
Author_Institution :
Fac. of Inf. & Commun., Central Queensland Univ., Rockhampton, Qld., Australia
Abstract :
In this paper, a general backpropagation learning framework for the training of feedforward neural networks is proposed. The convergence to global minimum under the framework is investigated using the Lyapunov stability theory. It is shown the existing feedforward neural network training algorithms are special cases of the proposed framework
Keywords :
Lyapunov methods; backpropagation; convergence; feedforward neural nets; Lyapunov stability theory; backpropagation learning framework; convergence; feedforward neural networks; global minimum; training algorithms; Backpropagation algorithms; Convergence; Data mining; Feedforward neural networks; Function approximation; Informatics; Lyapunov method; Neural networks; Neurons; Predictive models;
Conference_Titel :
Circuits and Systems, 2001. ISCAS 2001. The 2001 IEEE International Symposium on
Conference_Location :
Sydney, NSW
Print_ISBN :
0-7803-6685-9
DOI :
10.1109/ISCAS.2001.921407
