A constructive based hybrid training algorithm for feedforward neural networks

This paper presents a new learning algorithm for feedforward neural networks. This algorithm uses the vigilance parameter to generate the hidden layer neurons. This process improves the initial weight problem and the adaptive neurons of the hidden layer. The proposed approach is based on combined unsupervised and supervised learning. In this algorithm, the weights between input and hidden layers are firstly adjusted by Kohonen algorithm with fuzzy neighborhood, whereas the weights connecting hidden and output layers are adjusted using gradient descent method. Two simulation examples are provided to demonstrate the efficiency of the approach compared with a number of other methods.