On a Convex Logic Fragment for Learning and Reasoning
Authors:
- Francesco GianniniFGFrancesco Giannini
- Michelangelo DiligentiMDMichelangelo Diligenti
- Marco GoriMGMarco Gori
- Marco MagginiMMMarco Maggini
Preprint
Abstract
In this paper we introduce the convex fragment of {\L}ukasiewicz Logic and discuss its possible applications in different learning schemes. Indeed, the provided theoretical results are highly general, because they can be exploited in any learning framework involving logical constraints. The method is of particular interest since the fragment guarantees to deal with convex constraints, which are shown to be equivalent to a set of linear constraints. Within this framework, we are able to formulate learning with kernel machines as well as collective classification as a quadratic programming problem.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Semantic-based regularization for learning and inferenceArtificial Intelligence, 2017
- Learning and Reasoning with Logic Tensor Networks2016
- Bridging logic and kernel machinesMachine Learning, 2011
- Fast learning of relational kernelsMachine Learning, 2010
- Support Vector Inductive Logic ProgrammingLecture Notes in Computer Science, 2005
- Residuated fuzzy logics with an involutive negationArchive for Mathematical Logic, 2000
- Mathematical Principles of Fuzzy Logic1999
- Metamathematics of Fuzzy Logic1998
- Inductive Logic Programming: Theory and methodsThe Journal of Logic Programming, 1994
- A scaled conjugate gradient algorithm for fast supervised learningNeural Networks, 1993