A Study on Learning Mechanism for Neuron Networks with Weight-Function

摘要

In this paper a new neural network model with weightfunction is proposed. In the model, the weight is a function with adjustable parameters, and the sum of these weight functions as the neuron output. And according to BP algorithm, the learning algorithm of feed-forward neural network with weight-function neurons is studied. Simulation results show that, applying the back-propagation algorithm to the new neural network the better convergence rate can be obtained and in some applications the new neural network based on the weight-function neurons is superior to the BP network based on the MP neuron model,- so that it has a significant value in further research and application.