论文信息 - A system identification perspective on neural nets

A system identification perspective on neural nets

The authors review some of the basic system identification machinery to reveal connections with neural networks. In particular, they point to the role of regularization in dealing with model structures with many parameters, and show the links to overtraining in neural nets. Some provisional explanations for the success of neural nets are also offered.<<ETX>>

L. Ljung | J. Sjoberg | L. Ljung | J. Sjoberg

[1] Lennart Ljung,et al. Recursive methods for off-line identification , 1985 .

[2] L. Ljung,et al. Black-box Identification of Transfer Functions: Asymptotic Results for Increasing Model Order and Data Records , 1984 .

[3] A. Barron,et al. Statistical properties of artificial neural networks , 1989, Proceedings of the 28th IEEE Conference on Decision and Control,.

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

[5] L. Ljung,et al. Overtraining, Regularization, and Searching for Minimum in Neural Networks , 1992 .

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

[7] Grace Wahba,et al. THREE TOPICS IN ILL-POSED PROBLEMS , 1987 .