A novel link structure and learning algorithm of feedforward neural network

The links from hidden layer to output layer are expanded for improving the learning performance of neural network. Based on this, a new neural network structure is proposed and a learning algorithm is derived on it. Several n-parity, function approximation and pattern classification problem simulations are made to verify the effectiveness of the proposed method. The experimental results show that the proposed method has the dual merits of quick training speed and good generalization capability. It proves to be a very effective method.