Translating feed-forward nets to SOM-like maps
(2003) 14th ProRISC Workshop on Circuits, Systems and Signal Processing, 2003 p.447-452- 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.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/603852
- author
- vanderZwaag, B J ; Spaanenburg, Lambert LU and Slump, C
- organization
- publishing date
- 2003
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- keywords
- feature maps, selforganizing maps, Neural networks, rule extraction, character recognition.
- host publication
- Proceedings ProRisc?03
- pages
- 447 - 452
- conference name
- 14th ProRISC Workshop on Circuits, Systems and Signal Processing, 2003
- conference location
- Veldhoven, Netherlands
- conference dates
- 2003-11-26 - 2003-11-27
- ISBN
- 90-73461-39-1
- language
- English
- LU publication?
- yes
- id
- 2d468990-d93f-4b4c-b591-ce5fb5056bbb (old id 603852)
- date added to LUP
- 2016-04-04 13:37:01
- date last changed
- 2018-11-21 21:15:09
@inproceedings{2d468990-d93f-4b4c-b591-ce5fb5056bbb, abstract = {{A major disadvantage of feedforward neural<br/><br> 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<br/><br> transformation of a feed-forward network into a SOMlike<br/><br> structure such that its internal knowledge can be visually<br/><br> interpreted. This is particularly applicable to networks<br/><br> trained in the general classification problem domain.}}, author = {{vanderZwaag, B J and Spaanenburg, Lambert and Slump, C}}, booktitle = {{Proceedings ProRisc?03}}, isbn = {{90-73461-39-1}}, keywords = {{feature maps; selforganizing maps; Neural networks; rule extraction; character recognition.}}, language = {{eng}}, pages = {{447--452}}, title = {{Translating feed-forward nets to SOM-like maps}}, year = {{2003}}, }