Stage-oe-small.jpg

Article1895

Aus Aifbportal
Version vom 16. Oktober 2009, 22:41 Uhr von Nicole Arlt (Diskussion | Beiträge) (Wikipedia python library)
Wechseln zu:Navigation, Suche


Extracting Reduced Logic Programs from Artificial Neural Networks


Extracting Reduced Logic Programs from Artificial Neural Networks



Veröffentlicht: 2008 September

Journal: Applied Intelligence




Referierte Veröffentlichung

BibTeX




Kurzfassung
Artificial neural networks can be trained to perform excellently in many application areas. Whilst they can learn from raw data to solve sophisticated recognition and analysis problems, the acquired knowledge remains hidden within the network architecture and is not readily accessible for analysis or further use: Trained networks are black boxes. Recent research efforts therefore investigate the possibility to extract symbolic knowledge from trained networks, in order to analyze, validate, and reuse the structural insights gained implicitly during the training process. In this paper, we will study how knowledge in form of propositional logic programs can be obtained in such a way that the programs are as simple as possible-where simple is being understood in some clearly defined and meaningful way.

ISSN: 1573-7497
Download: Media:2008_1895_Lehmann_Extracting_Redu_1.pdf,Media:2008_1895_Lehmann_Extracting_Redu_2.pdf
DOI Link: 10.1007/s10489-008-0142-y

Projekt

ReaSem



Forschungsgruppe

Wissensmanagement


Forschungsgebiet

Neuro-symbolische Integration