Home |  ENGLISH |  Kontakt |  Impressum |  Anmelden |  KIT

Inproceedings1457

Aus Aifbportal

Wechseln zu: Navigation, Suche

(This page contains COinS metadata)

Using FCA for Encoding of Closure Operators into Neural Networks




Published: 2007 Juli
Herausgeber: Uta Priss, Simon Polovina, Richard Hill
Buchtitel: Conceptual Structures: Knowledge Architectures for Smart Applications, Proc. ICCS 2007
Ausgabe: 4604
Reihe: LNAI
Seiten: 321 -- 332
Verlag: Springer-Verlag
Erscheinungsort: Berlin Heidelberg
Referierte Veröffentlichung
BibTeX

Kurzfassung
After decades of concurrent development of symbolic and connectionist methods, recent years have shown intensifying efforts of integrating those two paradigms. This paper contributes to the development of methods for transferring present symbolic knowledge into connectionist representations. Motivated by basic ideas from formal concept analysis, we propose two ways of directly encoding closure operators on finite sets in a 3-layered feed forward neural network.

ISBN: 978-3-540-73680-6
ISSN: 0302-9743
Download: Media:2007_1457_Rudolph_Using_FCA_for_E_1.pdf



Forschungsgruppe

Wissensmanagement