Title :
A homotopy recursive algorithm for multilayer feedforward neural network
Author :
Dali, Yang ; Zemin, Liu ; Zheng, Zhou
Author_Institution :
Dept. of Inf. Eng., Beijing Univ. of Posts & Telecommun., China
Abstract :
This paper proposes a homotopy recursive backpropagation (BP) algorithm, which introduces the homotopy continuation method to the multilayer feedforward neural network so as to provide the global convergence and faster convergence speed than conventional BP algorithm for the feedforward neural network
Keywords :
backpropagation; convergence of numerical methods; feedforward neural nets; optimisation; global convergence; homotopy recursive algorithm; homotopy recursive backpropagation; multilayer feedforward neural network; optimal convergence; Algorithm design and analysis; Computer errors; Convergence; Feedforward neural networks; Gradient methods; Manifolds; Multi-layer neural network; Neural networks; Nonlinear systems; Telecommunication network topology;
Conference_Titel :
Speech, Image Processing and Neural Networks, 1994. Proceedings, ISSIPNN '94., 1994 International Symposium on
Print_ISBN :
0-7803-1865-X
DOI :
10.1109/SIPNN.1994.344887
