liu.seSearch for publications in DiVA
Change search
ReferencesLink to record
Permanent link

Direct link
Regularization Issues in Neural Network Models of Dynamical Systems
Linköping University, Department of Electrical Engineering, Automatic Control. Linköping University, The Institute of Technology.
1993 (English)Licentiate thesis, monograph (Other academic)
Abstract [en]

The latest era of neural networks started some ten years ago and the literature has been characterized by many successful applications, but the underlying theory is often omitted. In this thesis feed-forward neural networks are considered from a system identification point of view. Two nonlinear generalizations of the linear ARX and OE models are proposed and theoretically justifed.

Neural networks are often characterized by the fact that they use a fairly large amount of parameters. We address the problem how this can be done without the usual penalty in terms of a large variance error. We show that regularization is a key explanation, and that terminating a gradient search ("backpropagation") before the true criterion minimum is found is a way of achieving regularization. This theory also explains the concept of "overtraining" in neural nets. 

Place, publisher, year, edition, pages
Linköping: Linköping University , 1993. , 108 p.
Linköping Studies in Science and Technology. Thesis, ISSN 0280-7971 ; 366
National Category
Control Engineering
URN: urn:nbn:se:liu:diva-98085Local ID: Liu-TEK-LIC-1993:08ISBN: 91-7871-072-3OAI: diva2:652091
Available from: 2013-10-09 Created: 2013-09-29 Last updated: 2013-10-09Bibliographically approved

Open Access in DiVA

No full text

By organisation
Automatic ControlThe Institute of Technology
Control Engineering

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

Total: 38 hits
ReferencesLink to record
Permanent link

Direct link