Foundations of logic programming; (2nd extended ed.)
Foundations of logic programming; (2nd extended ed.)
Fractals everywhere
Knowledge-based artificial neural networks
Artificial Intelligence
Symbolic knowledge extraction from trained neural networks: a sound approach
Artificial Intelligence
Neural Networks for Pattern Recognition
Neural Networks for Pattern Recognition
Neural-Symbolic Learning System: Foundations and Applications
Neural-Symbolic Learning System: Foundations and Applications
Approximating the Semantics of Logic Programs by Recurrent Neural Networks
Applied Intelligence
The Connectionist Inductive Learning and Logic Programming System
Applied Intelligence
Neural Networks and Structured Knowledge: Rule Extraction andApplications
Applied Intelligence
Hybrid Neural Systems, revised papers from a workshop
Neural-symbolic intuitionistic reasoning
Design and application of hybrid intelligent systems
Rule Extraction from Recurrent Neural Networks: A Taxonomy and Review
Neural Computation
Connectionist model generation: A first-order approach
Neurocomputing
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
A fully connectionist model generator for covered first-order logic programs
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
A new approach and system for attentive mobile learning based on seamless migration
Applied Intelligence
A neural-symbolic cognitive agent for online learning and reasoning
IJCAI'11 Proceedings of the Twenty-Second international joint conference on Artificial Intelligence - Volume Volume Two
Perception processing for general intelligence: bridging the symbolic/subsymbolic gap
AGI'12 Proceedings of the 5th international conference on Artificial General Intelligence
Hi-index | 0.00 |
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.