Adjoint operator algorithms for faster learning in dynamical neural networks
Advances in neural information processing systems 2
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
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
NN'09 Proceedings of the 10th WSEAS international conference on Neural networks
COMUNICA: a question answering system for Brazilian Portuguese
COLING '10 Proceedings of the 23rd International Conference on Computational Linguistics: Demonstrations
Self-Adjustable Neural Network for speech recognition
Engineering Applications of Artificial Intelligence
Hi-index | 0.00 |
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.