G
Gadi Pinkas
Researcher at Washington University in St. Louis
Publications - 22
Citations - 955
Gadi Pinkas is an academic researcher from Washington University in St. Louis. The author has contributed to research in topics: Propositional calculus & Energy minimization. The author has an hindex of 12, co-authored 22 publications receiving 866 citations. Previous affiliations of Gadi Pinkas include Bar-Ilan University.
Papers
More filters
Posted Content
Neural-Symbolic Learning and Reasoning: A Survey and Interpretation
Tarek R. Besold,Artur S. d'Avila Garcez,Sebastian Bader,Howard Bowman,Pedro Domingos,Pascal Hitzler,Kai-Uwe Kuehnberger,Luis C. Lamb,Daniel Lowd,Priscila M. V. Lima,Leo de Penning,Gadi Pinkas,Hoifung Poon,Gerson Zaverucha +13 more
TL;DR: This joint survey reviews the personal ideas and views of several researchers on neural-symbolic learning and reasoning and presents the challenges facing the area and avenues for further research.
Proceedings ArticleDOI
Discovery of fraud rules for telecommunications—challenges and solutions
TL;DR: This work presents as an example a two-stage system based on adaptation of the C4.5 rule generator, with an additional rule selection mechanism, and experimental results indicate that this route is very promising.
Journal ArticleDOI
Reasoning, nonmonotonicity and learning in connectionist networks that capture propositional knowledge
TL;DR: An extended version of propositional calculus is developed and is demonstrated to be useful for nonmonotonic reasoning, dealing with conflicting beliefs and for coping with inconsistency generated by unreliable knowledge sources.
Proceedings ArticleDOI
Propositional non-monotonic reasoning and inconsistency in symmetric neural networks
TL;DR: This work defines a model-theoretic reasoning formalism that is naturally implemented on symmetric neural networks (like Hopfield networks or Boltzman machines) and sketches a connectionist inference engine that implements this reasoning paradigm.
Journal ArticleDOI
Symmetric Neural Networks and Propositional Logic Satisfiability
TL;DR: High-order models that use sigma-pi units are shown to be equivalent to the standard quadratic models with additional hidden units, and an algorithm to convert high-order networks to low-order ones is used to implement a satisfiability problem-solver on a connectionist network.