Search: id:"swepub:oai:DiVA.org:his-1267" >
Reducing Complexity...
Reducing Complexity of Rule Extraction from Prediction RNNs trough Domain Interaction
-
- Jacobsson, Henrik (author)
- Högskolan i Skövde,Institutionen för kommunikation och information
-
- Ziemke, Tom (author)
- Högskolan i Skövde,Institutionen för kommunikation och information
-
(creator_code:org_t)
- Skövde : Institutionen för kommunikation och information, 2003
- English 8 s.
-
Series: IKI Technical Reports ; HS-IDA-TR-03-007
- Related links:
-
https://his.diva-por... (primary) (Raw object)
-
show more...
-
https://urn.kb.se/re...
-
show less...
Abstract
Subject headings
Close
- This paper presents a quantitative investigation of the differences between rule extraction through breadth first search and through sampling the states of the RNN in interaction with its domain. We show that for an RNN trained to predict symbol sequences in formal grammar domains, the breadth first search is especially inefficient for languages sharing properties with realistic real world domains. We also identify some important research issues, needed to be resolved to ensure further development in the field of rule extraction from RNNs.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap -- Systemvetenskap, informationssystem och informatik (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Information Systems (hsv//eng)
Keyword
- Computer and systems science
- Data- och systemvetenskap
Publication and Content Type
- vet (subject category)
- rap (subject category)
To the university's database