Learning Recurrent ANFIS Using Stochastic Pattern Search Method
نویسندگان
چکیده
Pattern search learning is known for simplicity and faster convergence. However, one of the downfalls of this learning is the premature convergence problem. In this paper, we show how we can avoid the possibility of being trapped in a local pit by the introduction of stochastic value. This improved pattern search is then applied on a recurrent type neuro-fuzzy network (ANFIS) to solve time series prediction. Comparison with other method shows the effectiveness of the proposed method for this problem.
منابع مشابه
Hybrid GA Tuned RBF Based Neuro-Fuzzy Controller for Robotic Manipulator
In this paper performance of Puma 560 manipulator is being compared for hybrid gradient descent and least square method learning based ANFIS controller with hybrid Genetic Algorithm and Generalized Pattern Search tuned radial basis function based Neuro-Fuzzy controller. ANFIS which is based on Takagi Sugeno type Fuzzy controller needs prior knowledge of rule base while in radial basis function ...
متن کاملEvolutionary Search, Stochastic Policies with Memory, and Reinforcement Learning with Hidden State
Reinforcement Learning (RL) problems with hidden state present signiicant obstacles to prevailing RL methods. In this paper , we present experiments conducted using a straightforward approach to solving such problems that trains artiicial neural networks with recurrent connections to represent action policies using evolutionary search. We apply this method to two diierent benchmark problems. Th...
متن کاملHandwritten Nastaleeq Script Recognition with BLSTM-CTC and ANFIS method
A recurrent neural network (RNN) has been successfully applied for recognition of cursive handwritten documents, both in English and Arabic scripts. Ability of RNNs to model context in sequence data like speech and text makes them a suitable candidate to develop OCR systems for printed Nastaleeq scripts (including Nastaleeq for which no OCR system is available to date). In this work, we have pr...
متن کاملImproved Generalization in Recurrent Neural Networks Using the Tangent Plane Algorithm
The tangent plane algorithm for real time recurrent learning (TPA-RTRL) is an effective online training method for fully recurrent neural networks. TPA-RTRL uses the method of approaching tangent planes to accelerate the learning processes. Compared to the original gradient descent real time recurrent learning algorithm (GD-RTRL) it is very fast and avoids problems like local minima of the sear...
متن کاملDynamical multilayer neural networks that learn continuous trajectories
The feed-forward multilayer networks (perceptrons, radial basis function networks (RBF), probabilistic networks, etc.) are currently used as „static systems“ in pattern recognition, speech generation, identification and control, prediction, etc. (see, e. g. [1]). Theoretical works by several researchers, including [2] and [3] have proved that, even with one hidden layer, a perceptron neural net...
متن کامل