Unsaturated MLP neural networks training algorithm using a piecewise error function and adaptive learning rates

2008 ◽  
Author(s):  
Payman Moallem ◽  
S.Arvin Ayoughi
Keyword(s):  
Neural Networks ◽  
Adaptive Learning ◽  
Error Function ◽  
Training Algorithm ◽  
Learning Rates ◽  
Mlp Neural Networks

AN ULTRASONIC MOTOR SPEED CONTROL SCHEME BASED ON NEURAL NETWORKS AND ITERATIVE CONTROLLER

2004 ◽  
Vol 01 (03) ◽  
pp. 457-470
Author(s):  
X. H. SHI ◽  
Y. C. LIANG ◽  
X. XU
Keyword(s):  
Neural Networks ◽  
Adaptive Learning ◽  
Speed Control ◽  
Ultrasonic Motor ◽  
Random Disturbance ◽  
Motor Speed ◽  
Neural Network Controller ◽  
Learning Rates ◽  
Network Controller ◽  
Control Scheme

An ultrasonic motor speed control scheme is presented in this paper based on neural networks and iterative controller. Suitable ranges of the adaptive learning rates of neural network controller are presented through the theoretical analysis on the proposed model, which could guarantee its stability. The convergence of iterative controller is also discussed. Numerical results show that the control scheme is effective for various kinds of reference speeds of ultrasonic motors. Comparisons with the existing method show that the precision of control could be increased using the proposed method. Simulations also show that the proposed scheme is fairly robust against random disturbance to the control variables.

scholarly journals Convergence of an Online Split-Complex Gradient Algorithm for Complex-Valued Neural Networks

2010 ◽  
Vol 2010 ◽  
pp. 1-27
Author(s):  
Huisheng Zhang ◽  
Dongpo Xu ◽  
Zhiping Wang
Keyword(s):  
Neural Networks ◽  
Fixed Point ◽  
Adaptive Learning ◽  
Gradient Method ◽  
Error Function ◽  
Gradient Algorithm ◽  
Training Procedure ◽  
Weight Sequence ◽  
Complex Valued ◽  
Complex Gradient

The online gradient method has been widely used in training neural networks. We consider in this paper an online split-complex gradient algorithm for complex-valued neural networks. We choose an adaptive learning rate during the training procedure. Under certain conditions, by firstly showing the monotonicity of the error function, it is proved that the gradient of the error function tends to zero and the weight sequence tends to a fixed point. A numerical example is given to support the theoretical findings.

Decisional Autonomy of Approach and Landing Phase for Civil Aviation Aircraft using Dual Fuzzy Neural Network

2012 ◽  
Vol 476-478 ◽  
pp. 936-939 ◽  
Author(s):  
Kai Jun Xu
Keyword(s):  
Neural Network ◽  
Adaptive Learning ◽  
Gradient Descent ◽  
Fuzzy Neural Network ◽  
Error Function ◽  
Civil Aviation ◽  
Learning Rates ◽  
The Neural Network ◽  
Automatic Landing ◽  
Fuzzy Neural

This paper presents the dual fuzzy neural network, designed the decisional autonomy flight controller for civil aviation aircraft in approach and landing phase. Real-time learning method was applied to train the neural network using the gradient-descent of an error function to adaptively update weights. Adaptive learning rates were obtained through the analysis of Lyapunov stability to guarantee the convergence of learning. Conventional automatic landing system (ALS) can provide a smooth landing, which is essential to the comfort of passengers. However, these systems work only within a specified operational safety envelope. When the conditions are beyond the envelope, such as turbulence or wind shear, they often cannot be used. The objective of this paper is to investigate the use of dual fuzzy neural network in ALS and to make that system more intelligent.

Sign in / Sign up

Export Citation Format

Share Document