论文信息 - Weight value initialization for improving training speed in the backpropagation network

Weight value initialization for improving training speed in the backpropagation network

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.<<ETX>>

Jong Beom Ra | Young-Ik Kim | Y.K. Kim | J. Ra

[1] Robert A. Jacobs,et al. Increased rates of convergence through learning rate adaptation , 1987, Neural Networks.

[2] Bernard Widrow,et al. Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights , 1990, 1990 IJCNN International Joint Conference on Neural Networks.