Neural-symbolic intuitionistic reasoning

Authors:
Artur S. d'Avila Garcez;Luis C. Lamb;Dov M. Gabbay
Affiliations:
Dept. of Computing, City University, London, EC1V 0HB, UK;Instituto de Informática, UFRGS, Porto Alegre, RS, 91501-970, Brazil;Dept. of Computer Science, King's College, London WC2R2LS, UK
Venue:
Design and application of hybrid intelligent systems
Year:
2003

Citing 16
Cited 2

Foundations of logic programming; (2nd extended ed.)

Foundations of logic programming; (2nd extended ed.)
Temporal logic programming is complete and expressive

POPL '89 Proceedings of the 16th ACM SIGPLAN-SIGACT symposium on Principles of programming languages
Semantics of distributed definite clause programs

Theoretical Computer Science
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
Computational interpretations of linear logic

Theoretical Computer Science - Special volume of selected papers of the Sixth Workshop on the Mathematical Foundations of Programming Semantics, Kingston, Ont., Canada, May 1990
Reasoning about termination of pure Prolog programs

Information and Computation
Knowledge-based artificial neural networks

Artificial Intelligence
Preferred answer sets for extended logic programs

Artificial Intelligence
Knowledge-based neurocomputing

Knowledge-based neurocomputing
Symbolic knowledge extraction from trained neural networks: a sound approach

Artificial Intelligence
Modal logic

Modal logic
A modal analysis of staged computation

Journal of the ACM (JACM)
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
The common fragment of CTL and LTL

FOCS '00 Proceedings of the 41st Annual Symposium on Foundations of Computer Science

Extracting reduced logic programs from artificial neural networks

Applied Intelligence
The core method: connectionist model generation

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part II

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present a new computational model for intulitionistic logic. We use an enserable of Connectionist Inductive Learning and Logic Programming (C-ILP) neural networks to represent intuitionistic clauses, and show that for each intuitionistic program there exists a corresponding C-ILP ensemble such that the ensemble computes the fixed point of the program. This provides a massively parallel model for intuitionistic reasoning. In addition, C-ILP ensembles can be trained to adapt from examples using standard neural networks learning algorithms.