A stable online self-constructing recurrent neural network

Authors:
Qili Chen;Wei Chai;Junfei Qiao
Affiliations:
Intelligent Systems Institute, Electronic Information and Control Engineering, Beijing University of Technology, Beijing, China;Intelligent Systems Institute, Electronic Information and Control Engineering, Beijing University of Technology, Beijing, China;Intelligent Systems Institute, Electronic Information and Control Engineering, Beijing University of Technology, Beijing, China
Venue:
ISNN'11 Proceedings of the 8th international conference on Advances in neural networks - Volume Part III
Year:
2011

Citing 4
Cited 0

The identification of nonlinear biological systems: Wiener and Hammerstein cascade models

Biological Cybernetics
Identification of Nonlinear Systems Using Neural Networks and Polynomial Models: A Block-Oriented Approach (Lecture Notes in Control and Information Sciences)

Identification of Nonlinear Systems Using Neural Networks and Polynomial Models: A Block-Oriented Approach (Lecture Notes in Control and Information Sciences)
Online adaptive fuzzy neural identification and control of a class of MIMO nonlinear systems

IEEE Transactions on Fuzzy Systems
Direct adaptive controller for nonaffine nonlinear systems using self-structuring neural networks

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

A new online self-constructing recurrent neural network (SCRNN) model is proposed, of which the network structure could adjust according to the specific problem in real time. If the approximation performance of SCRNN is insufficient, SCRNN can create new neural network state to increase the learning ability. If the neural network state of SCRNN is redundant, it should be removed to simplify the structure of neural network and reduce the computation load;otherwise, if the hidden neuron of SCRNN is significant, it should be retained. Meanwhile, the feedback coefficient is adjusted by synaptic normalization mechanism to ensure the stability of network state. The proposed method effectively generates a recurrent neural model with a highly accurate and compact structure. Simulation results demonstrate that the proposed SCRNN has a self-organizing ability which can determine the structure and parameters of the recurrent neural network automatically. The network has a better stability.