Inelligible neural networks with BP-SOM
| Autor: | Weijters, A.J.M.M., Bosch, van den, A.P.J., Herik, van den, H.J., Nédellec, C., Rouveirol, C. |
|---|---|
| Přispěvatelé: | Information Systems IE&IS |
| Jazyk: | angličtina |
| Rok vydání: | 1998 |
| Zdroj: | Machine learning : ECML-98 : 10th European conference on machine learning, Chemnitz, Germany, April 21-23, 1998 : proceedings, 406-411 STARTPAGE=406;ENDPAGE=411;TITLE=Machine learning : ECML-98 : 10th European conference on machine learning, Chemnitz, Germany, April 21-23, 1998 : proceedings |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|