Extracting Explanations from Neural Networks

Abstract : The use of neural networks is still difficult in many application areas due to the lack of explanation facilities (the " black box " problem). An example of such applications is multiple criteria decision making (MCDM), applied to location problems having environmental impact. However, the concepts and methods presented are also applicable to other problem domains. These concepts show how to extract explanations from neural networks that are easily understandable for the user. Explanations obtained may in many cases even be better than those of expert systems. The INKA network presented in this paper is well adapted for MCDM problems, while also having properties that simplify the extraction of explanations compared to most other neural networks.
Type de document :
Communication dans un congrès
ICANN'95 Conference, Oct 1995, Paris, France. 1995
Liste complète des métadonnées

Contributeur : Florent Breuil <>
Soumis le : mercredi 4 septembre 2013 - 09:44:13
Dernière modification le : mardi 23 octobre 2018 - 14:36:04


  • HAL Id : emse-00857790, version 1


Kary Främling, Didier Graillot. Extracting Explanations from Neural Networks. ICANN'95 Conference, Oct 1995, Paris, France. 1995. 〈emse-00857790〉



Consultations de la notice