Modeling and prediction with a class of time delay dynamic neural networks

Authors:
Yasar Becerikli;Yusuf Oysal
Affiliations:
Department of Computer Engineering, Kocaeli University, Izmit, Turkey;Anadolu University, Computer Engineering Department, Eskisehir, Turkey
Venue:
Applied Soft Computing
Year:
2007

Citing 13
Cited 5

Adjoint operator algorithms for faster learning in dynamical neural networks

Advances in neural information processing systems 2
Global stability analysis in delayed Hopfield neural network models

Neural Networks
On stability of nonlinear continuous-time neural networks with delays

Neural Networks
Second-Order Methods for Neural Networks

Second-Order Methods for Neural Networks
Applied Numerical Methods with Software

Applied Numerical Methods with Software
Numerical Methods for Engineers: With Programming and Software Applications

Numerical Methods for Engineers: With Programming and Software Applications
Delay-dependent exponential stability analysis of delayed neural networks: an LMI approach

Neural Networks
A new approach to stability of neural networks with time-varying delays

Neural Networks
Intelligent optimal control with dynamic neural networks

Neural Networks
Learning state space trajectories in recurrent neural networks

Neural Computation
Prediction of a Lorenz chaotic attractor using two-layer perceptron neural network

Applied Soft Computing
A note on stability of analog neural networks with time delays

IEEE Transactions on Neural Networks
Training trajectories by continuous recurrent multilayer networks

IEEE Transactions on Neural Networks

Review of development of nonconventional neural architectures at the Czech technical university in Prague

NN'09 Proceedings of the 10th WSEAS international conference on Neural networks
Weighted least squares support vector machine local region method for nonlinear time series prediction

Applied Soft Computing
COMUNICA: a question answering system for Brazilian Portuguese

COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Demonstrations
Local recurrent sigmoidal-wavelet neurons in feed-forward neural network for forecasting of dynamic systems: Theory

Applied Soft Computing
Self-Adjustable Neural Network for speech recognition

Engineering Applications of Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a time delay dynamic neural network (TDDNN) to track and predict a chaotic time series systems. The application of artificial neural networks to dynamical systems has been constrained by the non-dynamical nature of popular network architectures. Many of the drawbacks caused by the algebraic structures can be overcome with TDDNNs. TDDNNs have time delay elements in their states. This approach provides the natural properties of physical systems. The minimization of a quadratic performance index is considered for trajectory tracking applications. Gradient computations are presented based on adjoint sensitivity analysis. The computational complexity is significantly less than direct method, but it requires a backward integration capability. We used Levenberg-Marquardt parameter updating method.