A system identification perspective on neural nets
- 2 January 2003
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 423-435
- https://doi.org/10.1109/nnsp.1992.253670
Abstract
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.<>Keywords
This publication has 7 references indexed in Scilit:
- Statistical properties of artificial neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Overtraining, regularization and searching for a minimum, with application to neural networksInternational Journal of Control, 1995
- Identification and control of dynamical systems using neural networksIEEE Transactions on Neural Networks, 1990
- Approximation by superpositions of a sigmoidal functionMathematics of Control, Signals, and Systems, 1989
- Recursive methods for off-line identificationInternational Journal of Control, 1985
- Black-box Identification of Transfer Functions: Asymptotic Results for Increasing Model Order and Data RecordsIMA Journal of Mathematical Control and Information, 1984
- Generalized Cross-Validation as a Method for Choosing a Good Ridge ParameterTechnometrics, 1979