Title :
Improved back-propagation algorithm for neural networks
Author :
Manjun, Liang ; Zhu, Shi
Author_Institution :
Comput & Inf. Dept., Hefei Univ. of Technol., China
Abstract :
An improved back-propagation (BP) algorithm for neural networks is proposed. This algorithm gives a faster learning speed as compared with the usual BP algorithm. This done by including a momentum method, a cumulative back-propagation method, and a composite method
Keywords :
backpropagation; neural nets; backpropagation algorithm; composite method; cumulative backpropagation method; learning speed; momentum method; neural networks; Algorithm design and analysis; Artificial neural networks; Circuits; Large-scale systems; Multi-layer neural network; Neural networks; Neurons; Nonlinear dynamical systems; Supervised learning; Writing;
Conference_Titel :
Industrial Technology, 1994., Proceedings of the IEEE International Conference on
Conference_Location :
Guangzhou
Print_ISBN :
0-7803-1978-8
DOI :
10.1109/ICIT.1994.467110
