Translating Feedforward Neural Nets to SOM-like Maps

Zwaag van der, Berend Jan and Spaanenburg, Lambert and Slump, Kees (2003) Translating Feedforward Neural Nets to SOM-like Maps. In: ProRISC 2003, 14th Workshop on Circuits, Systems and Signal Processing, 26-27 November 2003, Veldhoven, the Netherlands.

PDF
484Kb

Abstract:	A major disadvantage of feedforward neural networks is still the difficulty to gain insight into their internal functionality. This is much less the case for, e.g., nets that are trained unsupervised, such as Kohonen¿s self-organizing feature maps (SOMs). These offer a direct view into the stored knowledge, as their internal knowledge is stored in the same format as the input data that was used for training or is used for evaluation. This paper discusses a mathematical transformation of a feed-forward network into a SOMlike structure such that its internal knowledge can be visually interpreted. This is particularly applicable to networks trained in the general classification problem domain.
Item Type:	Conference or Workshop Item
Copyright:	© 2003 STW Technology Foundation
Faculty:	Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:	Signals and Systems (SAS)
Link to this item:	http://purl.utwente.nl/publications/46698
Export this item as:	BibTeX EndNote HTML Citation Reference Manager

Show download statistics for this publication

Repository Staff Only: item control page

Metis ID: 215828