Temporal learning rule and dynamic neural network model

2000 ◽  
Vol 111 (2-3) ◽  
pp. 209-218 ◽  
Author(s):  
Yukifumi Shigematsu ◽  
Gen Matsumoto
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Neural Network Model ◽  
Learning Rule ◽  
Dynamic Neural Network ◽  
Temporal Learning

An Improved RBF Neural Network for Short Term Load Forecasting

2014 ◽  
Vol 1008-1009 ◽  
pp. 709-713 ◽  
Author(s):  
Chuang Li ◽  
Zhi Qiang Liang ◽  
Min You Chen
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Discriminant Function ◽  
Neural Network Model ◽  
Rbf Neural Network ◽  
Load Forecasting ◽  
Static Model ◽  
Short Term ◽  
Dynamic Neural Network ◽  
Short Term Load Forecasting

Neural network is widely used in the load forecasting area,but the traditional methods of load forecasting usually base on static model,which cannot change as time goes on. And the accuracy is worse and worse. To solve the problem, a dynamic neural network model for load forecasting is proposed .By way of introduce Error discriminant function, to control the error of load forecasting and dynamically modify the predicting model. Through the contrast of the short-term load forecasting result based on static neural network model and dynamic neural network model proposed, the error of load forecasting is decrease effectively.

scholarly journals Identification of a Typical CSTR Using Optimal Focused Time Lagged Recurrent Neural Network Model with Gamma Memory Filter

2009 ◽  
Vol 2009 ◽  
pp. 1-7
Author(s):  
S. N. Naikwad ◽  
S. V. Dudul
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Recurrent Neural Network ◽  
Neural Network Model ◽  
Learning Rule ◽  
Continuous Stirred Tank Reactor ◽  
Back Propagation Algorithm ◽  
Data Set ◽  
Highly Nonlinear ◽  
Time Lagged

A focused time lagged recurrent neural network (FTLR NN) with gamma memory filter is designed to learn the subtle complex dynamics of a typical CSTR process. Continuous stirred tank reactor exhibits complex nonlinear operations where reaction is exothermic. It is noticed from literature review that process control of CSTR using neuro-fuzzy systems was attempted by many, but optimal neural network model for identification of CSTR process is not yet available. As CSTR process includes temporal relationship in the input-output mappings, time lagged recurrent neural network is particularly used for identification purpose. The standard back propagation algorithm with momentum term has been proposed in this model. The various parameters like number of processing elements, number of hidden layers, training and testing percentage, learning rule and transfer function in hidden and output layer are investigated on the basis of performance measures like MSE, NMSE, and correlation coefficient on testing data set. Finally effects of different norms are tested along with variation in gamma memory filter. It is demonstrated that dynamic NN model has a remarkable system identification capability for the problems considered in this paper. Thus FTLR NN with gamma memory filter can be used to learn underlying highly nonlinear dynamics of the system, which is a major contribution of this paper.

Sign in / Sign up

Export Citation Format

Share Document