论文信息 - Forward perturbation algorithm for a general class of recurrent network

Forward perturbation algorithm for a general class of recurrent network

This paper introduces a general class of dynamic network, the layered digital dynamic network. It then derives the forward perturbation algorithm for computing the gradient of the network error with respect to the weights of the network.

O. De Jesus | M.T. Hagan | M. Hagan | O. De Jesus

[1] Paul J. Werbos,et al. Backpropagation Through Time: What It Does and How to Do It , 1990, Proc. IEEE.

[2] Kumpati S. Narendra,et al. Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[3] M. Hagan,et al. TRAINING RECURRENT NETWORKS FOR FILTERING AND CONTROL , 1999 .

[4] Ronald J. Williams,et al. A Learning Algorithm for Continually Running Fully Recurrent Neural Networks , 1989, Neural Computation.

[5] K S Narendra,et al. IDENTIFICATION AND CONTROL OF DYNAMIC SYSTEMS USING NEURAL NETWORKS , 1990 .

[6] J. Magnus,et al. Matrix Differential Calculus with Applications in Statistics and Econometrics , 2019, Wiley Series in Probability and Statistics.

[7] P.H.G. Coelho. Training recurrent networks using Hessian information , 1995, Proceedings of 1995 IEEE International Symposium on Information Theory.