Comparison of four neural net learning methods for dynamic system identification

Authors:
S. -Z. Qin;H. -T. Su;T. J. McAvoy
Affiliations:
Dept. of Chem. Eng., Maryland Univ., College Park, MD;-;-
Venue:
IEEE Transactions on Neural Networks
Year:
1992

Citing 0
Cited 6

Prediction- and simulation-error based perceptron training: Solution space analysis and a novel combined training scheme

Neurocomputing
Recurrent neuro-fuzzy system for fault detection and isolation in nuclear reactors

Advanced Engineering Informatics
Prediction of a Lorenz chaotic attractor using two-layer perceptron neural network

Applied Soft Computing
Soft computing-based active vibration control of a flexible structure

Engineering Applications of Artificial Intelligence
Training of neural models for predictive control

Neurocomputing
Identification of nonlinear dynamics using a general spatio-temporal network

Mathematical and Computer Modelling: An International Journal

Quantified Score

Hi-index	0.00

Visualization

Abstract

Four types of neural net learning rules are discussed for dynamic system identification. It is shown that the feedforward network (FFN) pattern learning rule is a first-order approximation of the FFN-batch learning rule. As a result, pattern learning is valid for nonlinear activation networks provided the learning rate is small. For recurrent types of networks (RecNs), RecN-pattern learning is different from RecN-batch learning. However, the difference can be controlled by using small learning rates. While RecN-batch learning is strict in a mathematical sense, RecN-pattern learning is simple to implement and can be implemented in a real-time manner. Simulation results agree very well with the theorems derived. It is shown by simulation that for system identification problems, recurrent networks are less sensitive to noise