To search, Click below search items.


All Published Papers Search Service


An Algorithm of Two-Phase Learning for Eleman Neural Network to Avoid the Local Minima Problem


Zhiqiang Zhang, Zheng Tang


Vol. 7  No. 4  pp. 1-10


Eleman Neural Network have been efficient identification tool in many areas (classification and prediction fields) since they have dynamic memories. However, one of the problems often associated with this type of network is the local minima problem which usually occurs in the process of the learning. To solve this problem and speed up the process of the convergence, we propose an improved algorithm which includes two phases, a backpropagation phase and a gradient ascent phase. When network gets stuck in local minimum, the gradient ascent phase is performed in an attempt to fill up the local minimum valley by modifying parameter in a gradient ascent direction of the energy function. We apply this method to the Boolean Series Prediction Questions to demonstrate its validity. The simulation result shows that the proposed method can avoid the local minima problem and largely accelerate the speed of the convergence and get good results for the prediction tasks


Eleman Neural Network (ENN), Local Minima Problem, Gain parameter; Boolean Series Prediction Questions (BSPQ)