Internal Measuring Models in Trained Neural Networks for Parameter Estimation from Images

Feng, Tian-Jin and Houkes, Z. and Korsten, M.J. and Spreeuwers, L.J. (1992) Internal Measuring Models in Trained Neural Networks for Parameter Estimation from Images. In: 4th International Conference on Image Processing and its Applications, 7-9 Apr 1992, Maastricht, The Netherlands.

Preview

PDF
283Kb

Abstract:	The internal representations of 'learned' knowledge in neural networks are still poorly understood, even for backpropagation networks. The paper discusses a possible interpretation of learned knowledge of a network trained for parameter estimation from images. The outputs of the hidden layer are the internal components of the output parameters. The input-to-hidden weight maps, functioning as a kind of internal measuring model of the parameter components, include statistical features of the training set and seem to have a clear physical and geometrical meaning
Item Type:	Conference or Workshop Item
Copyright:	© 1992 IEEE Press
Faculty:	Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:	Signals and Systems (SAS)
Link to this item:	http://purl.utwente.nl/publications/16504
Export this item as:	BibTeX EndNote HTML Citation Reference Manager

Show download statistics for this publication

Repository Staff Only: item control page

Metis ID: 113389