Inelligible neural networks with BP-SOM

A.J.M.M. Weijters, A.P.J. Bosch, van den, H.J. Herik, van den

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/CongresprocedureConferentiebijdrageAcademicpeer review

1 Citaat (Scopus)

Samenvatting

Interpretation of models induced by artificial neural networks is often a difficult task. In this paper we focus on a relatively novel neural network architecture and learning algorithm, bp-som that offers possibilities to overcome this difficulty. It is shown that networks trained with BP-SOM show interesting regularities, in that hidden-unit activations become restricted to discrete values, and that the som part can be exploited for automatic rule extraction.
Originele taal-2Engels
TitelMachine learning : ECML-98 : 10th European conference on machine learning, Chemnitz, Germany, April 21-23, 1998 : proceedings
RedacteurenC. Nédellec, C. Rouveirol
Plaats van productieBerlin
UitgeverijSpringer
Pagina's406-411
ISBN van geprinte versie978-3-540-64417-0
DOI's
StatusGepubliceerd - 1998

Publicatie series

NaamLecture notes in artificial intelligence
Volume1398

Vingerafdruk

Duik in de onderzoeksthema's van 'Inelligible neural networks with BP-SOM'. Samen vormen ze een unieke vingerafdruk.

Citeer dit