A fully connectionist model generator for covered first-order logic programs

Authors:
Sebastian Bader;Pascal Hitzler;Steffen Hölldobler;Andreas Witzel
Affiliations:
International Center for Computational Logic, Technische Universität Dresden, Germany;AIFB, Universität Karlsruhe, Germany;International Center for Computational Logic, Technische Universität Dresden, Germany;Institute for Logic, Language and Computation, Universiteit van Amsterdam
Venue:
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Year:
2007

Citing 6
Cited 6

Foundations of logic programming

Foundations of logic programming
Connectionism and cognitive architecture: a critical analysis

Connections and symbols
Fractals everywhere

Fractals everywhere
Towards a theory of declarative knowledge

Foundations of deductive databases and logic programming
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

Connectionist model generation: A first-order approach

Neurocomputing
Learning and Memorizing Models of Logical Theories in a Hybrid Learning Device

Neural Information Processing
Learning from Inconsistencies in an Integrated Cognitive Architecture

Proceedings of the 2008 conference on Artificial General Intelligence 2008: Proceedings of the First AGI Conference
Logics and Networks for Human Reasoning

ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part II
Extracting reduced logic programs from artificial neural networks

Applied Intelligence
Embodied concept formation and reasoning via neural-symbolic integration

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a fully connectionist system for the learning of first-order logic programs and the generation of corresponding models: Given a program and a set of training examples, we embed the associated semantic operator into a feed-forward network and train the network using the examples. This results in the learning of first-order knowledge while damaged or noisy data is handled gracefully.