Search: onr:"swepub:oai:DiVA.org:his-1267" >
Reducing Complexity...
-
Jacobsson, HenrikHögskolan i Skövde,Institutionen för kommunikation och information
(author)
Reducing Complexity of Rule Extraction from Prediction RNNs trough Domain Interaction
Publisher, publication year, extent ...
-
Skövde :Institutionen för kommunikation och information,2003
-
8 s.
-
electronicrdacarrier
Numbers
-
LIBRIS-ID:oai:DiVA.org:his-1267
-
https://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-1267URI
Supplementary language notes
-
Language:English
-
Summary in:English
Part of subdatabase
Classification
-
Subject category:vet swepub-contenttype
-
Subject category:rap swepub-publicationtype
Series
-
IKI Technical Reports ;HS-IDA-TR-03-007
Notes
-
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 and genre
Added entries (persons, corporate bodies, meetings, titles ...)
-
Ziemke, TomHögskolan i Skövde,Institutionen för kommunikation och information(Swepub:his)ziet
(author)
-
Högskolan i SkövdeInstitutionen för kommunikation och information
(creator_code:org_t)
Internet link
To the university's database