Extracting Reduced Logic Programs from Artificial Neural Networks

TitleExtracting Reduced Logic Programs from Artificial Neural Networks
Publication TypeConference Paper
Year of Publication2005
AuthorsJens Lehmann, Sebastian Bader

Artificial neural networks can be trained to perform excellently in many application areas. While 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.

Full Text

Jens Lehmann, Sebastian Bader, Pascal Hitzler. 'Extracting Reduced Logic Programs from Artificial Neural Networks.'Applied Intelligence, Volume 32.3 2010: 249-266
research center: Knowledge Engineering Lab
pages: 249-266
year: 2010
hasURL: http://knoesis.wright.edu/library/download/Extracting_Reduced_Logic_Prog...
hasBookTitle: Applied Intelligence