Article979: Unterschied zwischen den Versionen
K (Added from ontology) |
K (Added from ontology) |
||
Zeile 15: | Zeile 15: | ||
|Title=The Integration of Connectionism and First-Order Knowledge Representation and Reasoning as a Challenge for Artificial Intelligence | |Title=The Integration of Connectionism and First-Order Knowledge Representation and Reasoning as a Challenge for Artificial Intelligence | ||
|Year=2006 | |Year=2006 | ||
− | |Month= | + | |Month=Januar |
|Journal=Information | |Journal=Information | ||
|Note=Invited paper | |Note=Invited paper | ||
Zeile 38: | Zeile 38: | ||
|Downloadlink PDF=http://www.aifb.uni-karlsruhe.de/WBS/phi/pub/chall05.pdf | |Downloadlink PDF=http://www.aifb.uni-karlsruhe.de/WBS/phi/pub/chall05.pdf | ||
|Link extern= | |Link extern= | ||
− | |Forschungsgebiet= | + | |Forschungsgebiet=Künstliche Intelligenz, Neuro-symbolische Integration, Logik, Maschinelles Lernen, Logikprogrammierung, |
|Projekt=SmartWeb, KnowledgeWeb, | |Projekt=SmartWeb, KnowledgeWeb, | ||
|Forschungsgruppe= | |Forschungsgruppe= | ||
}} | }} |
Version vom 15. Juli 2009, 00:46 Uhr
The Integration of Connectionism and First-Order Knowledge Representation and Reasoning as a Challenge for Artificial Intelligence
The Integration of Connectionism and First-Order Knowledge Representation and Reasoning as a Challenge for Artificial Intelligence
Veröffentlicht: 2006 Januar
Journal: Information
Nummer: 1
Volume: 9
Bemerkung: Invited paper
Referierte Veröffentlichung
Kurzfassung
Intelligent systems based on first-order logic on the one hand, and
on artificial neural networks (also called connectionist systems) on the
other, differ substantially. It would be very desirable to combine the robust
neural networking machinery with symbolic knowledge representation
and reasoning paradigms like logic programming in such a way that
the strengths of either paradigm will be retained. Current state-of-the-art
research, however, fails by far to achieve this ultimate goal. As one of
the main obstacles to be overcome we perceive the question how symbolic
knowledge can be encoded by means of connectionist systems: Satisfactory
answers to this will naturally lead the way to knowledge extraction
algorithms and to integrated neural-symbolic systems.
ISSN: 1343-4500
Maschinelles Lernen, Neuro-symbolische Integration, Logik, Logikprogrammierung, Künstliche Intelligenz