Open AccessProceedings Article
Distributed Knowledge Representation in Neural-Symbolic Learning Systems: A Case Study
Artur S. d'Avila Garcez,Luis C. Lamb,Krysia Broda,Dov M. Gabbay +3 more
- pp 271-275
TLDR
This paper shows how neural networks can represent symbolic distributed knowledge, acting as multiagent systems with learning capability (a key feature of neural networks), and applies the approach to the well-known muddy children puzzle.Abstract:
Neural-symbolic integration concerns the integration of symbolic and connectionist systems. Distributed knowledge representation is traditionally seen under a purely symbolic perspective. In this paper, we show how neural networks can represent symbolic distributed knowledge, acting as multiagent systems with learning capability (a key feature of neural networks). We then apply our approach to the well-known muddy children puzzle, a problem used as a testbed for distributed knowledge representation formalisms. Finally, we sketch a full solution to this problem by extending our approach to deal with knowledge evolution over time.read more
Citations
More filters
Proceedings Article
Reasoning about Time and Knowledge in Neural Symbolic Learning Systems
TL;DR: This work presents a Translation Algorithm from temporal rules to neural networks, and shows that the networks compute a fixed-point semantics of the rules.
Journal ArticleDOI
A connectionist computational model for epistemic and temporal reasoning
TL;DR: This article shows that nonclassical logics, in particular propositional temporal logic and combinations of temporal and epistemic reasoning, can be effectively computed by artificial neural networks.
Journal ArticleDOI
Connectionist computations of intuitionistic reasoning
TL;DR: This paper uses ensembles of neural networks to represent intuitionistic theories, and shows that for each intuitionistic theory and intuitionistic modal theory there exists a corresponding neural network ensemble that computes a fixed-point semantics of the theory.
Proceedings Article
Neural-symbolic intuitionistic reasoning
TL;DR: A new computational model for intulitionistic logic is presented, using an enserable of Connectionist Inductive Learning and Logic Programming neural networks to represent intuitionistic clauses, and it is shown that for each intuitionistic program there exists a corresponding C-ILP ensemble such that the ensemble computes the fixed point of the program.
Book ChapterDOI
Cognitive Algorithms and Systems: Reasoning and Knowledge Representation
TL;DR: The goal is to provide computational models with integrated reasoning capabilities, where the neural networks offer the machinery for cognitive reasoning and learning while symbolic logic offers explanations to the neural models facilitating the necessary interaction with the world and other systems.
References
More filters
Book
Reasoning About Knowledge
TL;DR: Reasoning About Knowledge is the first book to provide a general discussion of approaches to reasoning about knowledge and its applications to distributed systems, artificial intelligence, and game theory.
Book
An Introduction to Modal Logic
Max J. Cresswell,G. E. Hughes +1 more
TL;DR: This long-awaited book replaces Hughes and Cresswell's two classic studies of modal logic with all the new developments that have taken place since 1968 in both modal propositional logic and modal predicate logic, without sacrificing clarity of exposition and approachability.
Book
Logic in Computer Science: Modelling and Reasoning about Systems
Michael Huth,Mark Ryan +1 more
TL;DR: This book provides a simple and clear presentation, covering propositional and predicate logic and some specialized logics used for reasoning about the correctness of computer systems.
Posted Content
Reasoning About Knowledge
TL;DR: Reasoning about knowledge as discussed by the authors provides a general discussion of approaches to reasoning about knowledge and its applications to distributed systems, artificial intelligence, and game theory, and brings eight years of work by the authors into a cohesive framework for understanding and analyzing knowledge that is intuitive, mathematically well founded, useful in practice, and widely applicable.