TY - CHAP T1 - Neural-Symbolic Learning and Reasoning: A Survey and Interpretation T2 - Neuro-Symbolic Artificial Intelligence: The State of the Art Y1 - 2022 A1 - Tarek R. Besold A1 - Artur S. d'Avila Garcez A1 - Sebastian Bader A1 - Howard Bowman A1 - Pedro Domingos A1 - Pascal Hitzler A1 - Kai-Uwe Kühnberger A1 - Luís C. Lamb A1 - Daniel Lowd A1 - Priscila Machado Vieira Lima A1 - Leo de Penning A1 - Gadi Pinkas A1 - Hoifung Poon A1 - Gerson Zaverucha JF - Neuro-Symbolic Artificial Intelligence: The State of the Art PB - IOS Press CY - Amsterdam ER - TY - BOOK T1 - Logik und Logikprogrammierung Band 2: Aufgaben und Lösungen Y1 - 2011 A1 - Steffen Hölldobler A1 - Sebastian Bader A1 - Bertram Fronhöfer A1 - Ursula Hans A1 - Pascal Hitzler A1 - Markus Krötzsch A1 - Tobias Pietzsch PB - Synchron Verlag CY - Heidelberg, Germany ER - TY - JOUR T1 - Extracting Reduced Logic Programs from Artificial Neural Networks JF - Applied Intelligence Y1 - 2010 A1 - Jens Lehmann A1 - Sebastian Bader A1 - Pascal Hitzler AB -

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.

VL - 32 UR - http://dx.doi.org/10.1007/s10489-008-0142-y ER -