Reasoning, nonmonotonicity and learning in connectionist networks that capture propositional knowledge

DOI10.1016/0004-3702(94)00032-VzbMath1013.68505MaRDI QIDQ1855237

Gadi Pinkas

Publication date: 4 February 2003

Published in: Artificial Intelligence (Search for Journal in Brave)

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

68T27: Logic in artificial intelligence

03B70: Logic in computer science

Related Items

Artificial nonmonotonic neural networks, \(\text{DA}^2\) merging operators, Compiling propositional weighted bases, How to decide what to do?, Nonmonotonic inferences and neural networks, Sequential inference with reliable observations: Learning to construct force-dynamic models, Recurrent neural networks with backtrack-points and negative reinforcement applied to cost-based abduction

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A mathematical treatment of defeasible reasoning and its implementation.
• ``Neural computation of decisions in optimization problems
• On the stability of the travelling salesman problem algorithm of Hopfield and Tank
• A logical framework for default reasoning
• A logic for default reasoning
• Circumscription - a form of non-monotonic reasoning
• Erratum to: ``What does a conditional knowledge base entail?
• Some results on the computational complexity of symmetric connectionist networks.
• On inference from inconsistent premisses
• Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
• A theory of the learnable
• Neural networks and physical systems with emergent collective computational abilities.
• Neurons with graded response have collective computational properties like those of two-state neurons.
• A Machine-Oriented Logic Based on the Resolution Principle
• A Computing Procedure for Quantification Theory