Analysis of Neural Networks in Terms of Domain Functions

Share/Save/Bookmark

Zwaag, Berend Jan van der and Slump, Cees and Spaanenburg, Lambert (2002) Analysis of Neural Networks in Terms of Domain Functions. In: 3rd IEEE Benelux Signal Processing Symposium, SPS, March 21-22, 2002, Leuven, Belgium (pp. pp. 237-240).

open access
[img]
Preview
PDF
143kB
Abstract:Despite their success-story, artificial neural networks have one major disadvantage compared to other techniques: the inability to explain comprehensively how a trained neural network reaches its output; neural networks are not only (incorrectly) seen as a "magic tool" but possibly even more as a mysterious "black box". Although much research has already been done to "open the box," there is a notable hiatus in known publications on analysis of neural networks. So far, mainly sensitivity analysis and rule extraction methods have been used to analyze neural networks. However, these can only be applied in a limited subset of the problem domains where neural network solutions are encountered. In this paper we propose a wider applicable method which, for a given problem domain, involves identifying basic functions with which users in that domain are already familiar, and describing trained neural networks, or parts thereof, in terms of those basic functions. This will provide a comprehensible description of the neural network's function and, depending on the chosen base functions, it may also provide an insight into the neural network' s inner "reasoning." It could further be used to optimize neural network systems. An analysis in terms of base functions may even make clear how to (re)construct a superior system using those base functions, thus using the neural network as a construction advisor.
Item Type:Conference or Workshop Item
Additional information:SAS 022N02
Faculty:
Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:
Link to this item:http://purl.utwente.nl/publications/43135
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page

Metis ID: 205956