BACKPROPAGATION LEARNING ALGORITHM WITH DIFFERENT LEARNING COEFFICIENTS FOR EACH LAYER

When considering the algorithm of error backpropagation learning, it i s seen that the learning of each layer is not completed independently. This paper proposes a DLBP learning algorithm which uses different le arning coefficients for each layer. By changing the ratio of the learn ing coefficients, the following can be controlled: the learning progre ss of the hidden units; the influence of the hidden units on the netwo rk. With DLBP learning, we can construct the corresponding networks to the different requirement such as; to obtain a network with small num ber of hidden units; and to obtain a fault tolerant network.