A Novel Learning Method for Elman Neural Network Using Local Search
نویسندگان
چکیده
− 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.
منابع مشابه
A Differential Evolution and Spatial Distribution based Local Search for Training Fuzzy Wavelet Neural Network
Abstract Many parameter-tuning algorithms have been proposed for training Fuzzy Wavelet Neural Networks (FWNNs). Absence of appropriate structure, convergence to local optima and low speed in learning algorithms are deficiencies of FWNNs in previous studies. In this paper, a Memetic Algorithm (MA) is introduced to train FWNN for addressing aforementioned learning lacks. Differential Evolution...
متن کاملTraffic Signal Prediction Using Elman Neural Network and Particle Swarm Optimization
Prediction of traffic is very crucial for its management. Because of human involvement in the generation of this phenomenon, traffic signal is normally accompanied by noise and high levels of non-stationarity. Therefore, traffic signal prediction as one of the important subjects of study has attracted researchers’ interests. In this study, a combinatorial approach is proposed for traffic signal...
متن کاملTwo Novel Learning Algorithms for CMAC Neural Network Based on Changeable Learning Rate
Cerebellar Model Articulation Controller Neural Network is a computational model of cerebellum which acts as a lookup table. The advantages of CMAC are fast learning convergence, and capability of mapping nonlinear functions due to its local generalization of weight updating, single structure and easy processing. In the training phase, the disadvantage of some CMAC models is unstable phenomenon...
متن کاملOptimizing Weights in Elman Recurrent Neural Networks with Wolf Search Algorithm
This paper presents a Metahybrid algorithm that consists of the dual combination of Wolf Search (WS) and Elman Recurrent Neural Network (ERNN). ERNN is one of the most efficient feed forward neural network learning algorithm. Since ERNN uses gradient descent technique during the training process; therefore, it is not devoid of local minima and slow convergence problem. This paper used a new met...
متن کاملTraining Elman Neural Network for Dynamical System Identification Using Stochastic Dynamic Batch Local Search Algorithm
In this paper, we propose a Stochastic Dynamic Batch Local Search (SDBLS) algorithm to train Elman Neural Network (ENN) for Dynamic Systems Identification (DSI). First, we propose a new Batch Local Search (BLS) algorithm for ENN from a new angle instead of traditional Back Propagation (BP) based gradient descent technique, then add the stochastic dynamic signal into the network in order to avoi...
متن کامل