DocumentCode
3416455
Title
A system identification perspective on neural nets
Author
Ljung, Lennart ; Sjöberg, Jonas
Author_Institution
Dept. of Electr. Eng., Linkoping Univ., Sweden
fYear
1992
fDate
31 Aug-2 Sep 1992
Firstpage
423
Lastpage
435
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
identification; neural nets; model structures; neural nets; overtraining; regularization; system identification; Art; Buildings; Footwear; Machinery; Mathematical model; Neural networks; Signal processing; Statistics; System identification; Zinc;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks for Signal Processing [1992] II., Proceedings of the 1992 IEEE-SP Workshop
Conference_Location
Helsingoer
Print_ISBN
0-7803-0557-4
Type
conf
DOI
10.1109/NNSP.1992.253670
Filename
253670
Link To Document