论文信息 - A Multilayer Real-Time Recurrent Learning Algorithm for Improved Convergence - 字舞流文

A Multilayer Real-Time Recurrent Learning Algorithm for Improved Convergence

In this paper an algorithm is described, which is based on the Real-Time Recurrent Learning (RTRL) algorithm by Williams and Zipser

Jacques Ludik | Kürt Meert | K. Meert | J. Ludik

[1] Barak A. Pearlmutter. Gradient calculations for dynamic recurrent neural networks: a survey , 1995, IEEE Trans. Neural Networks.

[2] George Cybenko,et al. Approximation by superpositions of a sigmoidal function , 1992, Math. Control. Signals Syst..

[3] Yuichi Nakamura,et al. Approximation of dynamical systems by continuous time recurrent neural networks , 1993, Neural Networks.

[4] K. Nakayama,et al. Probabilistic memory capacity of recurrent neural networks , 1996, Proceedings of International Conference on Neural Networks (ICNN'96).

[5] Amir F. Atiya,et al. Application of the recurrent multilayer perceptron in modeling complex process dynamics , 1994, IEEE Trans. Neural Networks.

[6] Lee A. Feldkamp,et al. Neurocontrol of nonlinear dynamical systems with Kalman filter trained recurrent networks , 1994, IEEE Trans. Neural Networks.

[7] C. Lee Giles,et al. Experimental Comparison of the Effect of Order in Recurrent Neural Networks , 1993, Int. J. Pattern Recognit. Artif. Intell..

[8] Ronald J. Williams,et al. Experimental Analysis of the Real-time Recurrent Learning Algorithm , 1989 .