A System Identification Perspective on Neural Nets
1992 (English)Report (Other academic)
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.
Place, publisher, year, edition, pages
Linköping: Linköping University , 1992.
LiTH-ISY-I, ISSN 8765-4321 ; 1373
Identification, Neural nets
IdentifiersURN: urn:nbn:se:liu:diva-55558OAI: oai:DiVA.org:liu-55558DiVA: diva2:316360