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

Direct link
Implicitly and Explicitly ConstrainedOptimization Problems for Training of Recurrent Neural Networks
Linköping University, Department of Management and Engineering, Solid Mechanics. Linköping University, Faculty of Science & Engineering.
2014 (English)Conference paper (Refereed)
Abstract [en]

Training of recurrent neural networks is typically formulated as unconstrained optimization problems. There is, however, an implicit constraint stating that the equations of state must be satisfied at every iteration in the optimization process. Such constraints can make a problem highly non-linear and thus difficult to solve. A potential remedy is to reformulate the problem into one in which the parameters and state are treated as independent variables and all constraints appear explicitly. In this paper we compare an implicitly and an explicitly constrained formulation of the same problem. Reported numerical results suggest that the latter is in some respects superior.

Place, publisher, year, edition, pages
2014. 461-466 p.
National Category
Computational Mathematics
Identifiers
URN: urn:nbn:se:liu:diva-125064ISBN: 978-287419095-7OAI: oai:DiVA.org:liu-125064DiVA: diva2:902683
Conference
22nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning. Bruges (Belgium), 23-25 April 2014,
Available from: 2016-02-12 Created: 2016-02-12 Last updated: 2016-02-24

Open Access in DiVA

No full text

Other links

link

Search in DiVA

By author/editor
Thore, Carl-Johan
By organisation
Solid MechanicsFaculty of Science & Engineering
Computational Mathematics

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: 2 hits
ReferencesLink to record
Permanent link

Direct link