期刊名称：Neural Information Processing: Letters and Reviews
电子版ISSN：1738-2532
出版年度：2007
卷号：11
期号：8
页码：181-188
出版社：Neural Information Processing
摘要：Elman Neural Network (ENN) have been efficient identification tool in many areas since they have dynamic
memories. However, the local minima problem usually occurs in the process of the learning because of the
employed back propagation algorithm. In this paper, we propose a novel learning method for ENN by introducing
adaptive learning parameter into the traditional local search algorithm. The proposed learning network requires
less memory and it is able to overcome the disadvantages of the gradient descent. Meanwhile it is also able to
accelerates the speed of the convergence and avoid the local minima problem in a certain extent. We apply the
new method to the Boolean Series Prediction Questions to demonstrate its validity. Simulation results show that
the proposed algorithm has a better ability to find the global minimum than back propagation algorithm within
reasonable time.
关键词：Elman Neural Network (ENN), Local Search (LS) Method, Adaptive Learning Parameter, Boolean Series Prediction Question (BSPQ)
