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
Original language | English |
---|---|
Title of host publication | Proceedings 4th International Conference on Image Processing and its Applications |
Place of Publication | Maastricht, The Netherlands |
Publisher | IEEE |
Pages | 230-233 |
Number of pages | 4 |
ISBN (Print) | 0-85296-543-5 |
Publication status | Published - 7 Apr 1992 |
Event | 4th International Conference on Image Processing and its Applications 1992 - Maastricht, Netherlands Duration: 7 Apr 1992 → 9 Apr 1992 |
Publication series
Name | |
---|---|
Publisher | IEEE Press |
Conference
Conference | 4th International Conference on Image Processing and its Applications 1992 |
---|---|
Country/Territory | Netherlands |
City | Maastricht |
Period | 7/04/92 → 9/04/92 |
Keywords
- IR-16504
- METIS-113389