Analysis of Neural Networks through Base Functions

Share/Save/Bookmark

Zwaag, B.J. van der and Slump, C.H. and Spaanenburg, L. (2002) Analysis of Neural Networks through Base Functions. In: Lerende Oplossingen. Technologiestichting STW 05 30-01, Nijmegen, The Netherlands, pp. 34-35.

open access
[img]
Preview
PDF
94kB
Abstract:Problem statement. Despite their success-story, 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" [1]. This is an important aspect of the functionality of any technology, as users will be interested in "how it works" before trusting it completely. 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.
Item Type:Book Section
Additional information:031.02
Copyright:© STW Technology Foundation
Faculty:
Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:
Link to this item:http://purl.utwente.nl/publications/43371
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page

Metis ID: 206438