Gradient based adaptive regularization

Robert Eigenmann, Josef A. Nossek

Research output: Contribution to conferencePaperpeer-review

5 Scopus citations

Abstract

A technique to optimize regularization parameters for a given supervised training problem is presented. A training database is applied to minimize a regularized cost function, and a validation database is used to estimate and optimize generalization properties by means of a modification of regularization. The performance is validated for a vowel classification task and compared to other approaches.

Original languageEnglish
Pages87-94
Number of pages8
StatePublished - 1999
Externally publishedYes
EventProceedings of the 1999 9th IEEE Workshop on Neural Networks for Signal Processing (NNSP'99) - Madison, WI, USA
Duration: 23 Aug 199925 Aug 1999

Conference

ConferenceProceedings of the 1999 9th IEEE Workshop on Neural Networks for Signal Processing (NNSP'99)
CityMadison, WI, USA
Period23/08/9925/08/99

Fingerprint

Dive into the research topics of 'Gradient based adaptive regularization'. Together they form a unique fingerprint.

Cite this