Title :
Weight value initialization for improving training speed in the backpropagation network
Author :
Kim, Y.K. ; Ra, J.B.
Author_Institution :
Dept. of Electr. Eng., Korea Adv. Inst. of Sci. & Technol., Seoul, South Korea
Abstract :
A method for initialization of the weight values of multilayer feedforward neural networks is proposed to improve the learning speed of a network. The proposed method suggests the minimum bound of the weights based on dynamics of decision boundaries, which is derived from the generalized delta rule. Computer simulation in several neural network models showed that the proper selection of the initial weight values improves the learning ability and contributed to fast convergence
Keywords :
convergence; learning systems; neural nets; backpropagation network; fast convergence; learning ability; multilayer feedforward neural networks; training speed; weight value initialisation; Backpropagation algorithms; Cellular neural networks; Equations; Intelligent networks; Least squares approximation; Multidimensional systems;
Conference_Titel :
Neural Networks, 1991. 1991 IEEE International Joint Conference on
Print_ISBN :
0-7803-0227-3
DOI :
10.1109/IJCNN.1991.170747
