Search: id:"swepub:oai:lup.lub.lu.se:2d468990-d93f-4b4c-b591-ce5fb5056bbb" >
Translating feed-fo...
Translating feed-forward nets to SOM-like maps
-
vanderZwaag, B J (author)
-
- Spaanenburg, Lambert (author)
- Lund University,Lunds universitet,Institutionen för elektro- och informationsteknik,Institutioner vid LTH,Lunds Tekniska Högskola,Department of Electrical and Information Technology,Departments at LTH,Faculty of Engineering, LTH
-
Slump, C (author)
-
(creator_code:org_t)
- 2003
- 2003
- English.
-
In: Proceedings ProRisc?03. - 9073461391 ; , s. 447-452
- Related links:
-
https://lup.lub.lu.s...
Abstract
Subject headings
Close
- 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.
Subject headings
- TEKNIK OCH TEKNOLOGIER -- Elektroteknik och elektronik (hsv//swe)
- ENGINEERING AND TECHNOLOGY -- Electrical Engineering, Electronic Engineering, Information Engineering (hsv//eng)
Keyword
- feature maps
- selforganizing maps
- Neural networks
- rule extraction
- character recognition.
Publication and Content Type
- kon (subject category)
- ref (subject category)
Find in a library
To the university's database