Cargando…

Propositional Kernels

The pervasive presence of artificial intelligence (AI) in our everyday life has nourished the pursuit of explainable AI. Since the dawn of AI, logic has been widely used to express, in a human-friendly fashion, the internal process that led an (intelligent) system to deliver a specific output. In th...

Descripción completa

Detalles Bibliográficos
Autores principales: Polato, Mirko, Aiolli, Fabio
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8391199/
https://www.ncbi.nlm.nih.gov/pubmed/34441160
http://dx.doi.org/10.3390/e23081020
_version_ 1783743216611229696
author Polato, Mirko
Aiolli, Fabio
author_facet Polato, Mirko
Aiolli, Fabio
author_sort Polato, Mirko
collection PubMed
description The pervasive presence of artificial intelligence (AI) in our everyday life has nourished the pursuit of explainable AI. Since the dawn of AI, logic has been widely used to express, in a human-friendly fashion, the internal process that led an (intelligent) system to deliver a specific output. In this paper, we take a step forward in this direction by introducing a novel family of kernels, called Propositional kernels, that construct feature spaces that are easy to interpret. Specifically, Propositional Kernel functions compute the similarity between two binary vectors in a feature space composed of logical propositions of a fixed form. The Propositional kernel framework improves upon the recent Boolean kernel framework by providing more expressive kernels. In addition to the theoretical definitions, we also provide an algorithm (and the source code) to efficiently construct any propositional kernel. An extensive empirical evaluation shows the effectiveness of Propositional kernels on several artificial and benchmark categorical data sets.
format Online
Article
Text
id pubmed-8391199
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-83911992021-08-28 Propositional Kernels Polato, Mirko Aiolli, Fabio Entropy (Basel) Article The pervasive presence of artificial intelligence (AI) in our everyday life has nourished the pursuit of explainable AI. Since the dawn of AI, logic has been widely used to express, in a human-friendly fashion, the internal process that led an (intelligent) system to deliver a specific output. In this paper, we take a step forward in this direction by introducing a novel family of kernels, called Propositional kernels, that construct feature spaces that are easy to interpret. Specifically, Propositional Kernel functions compute the similarity between two binary vectors in a feature space composed of logical propositions of a fixed form. The Propositional kernel framework improves upon the recent Boolean kernel framework by providing more expressive kernels. In addition to the theoretical definitions, we also provide an algorithm (and the source code) to efficiently construct any propositional kernel. An extensive empirical evaluation shows the effectiveness of Propositional kernels on several artificial and benchmark categorical data sets. MDPI 2021-08-07 /pmc/articles/PMC8391199/ /pubmed/34441160 http://dx.doi.org/10.3390/e23081020 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Polato, Mirko
Aiolli, Fabio
Propositional Kernels
title Propositional Kernels
title_full Propositional Kernels
title_fullStr Propositional Kernels
title_full_unstemmed Propositional Kernels
title_short Propositional Kernels
title_sort propositional kernels
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8391199/
https://www.ncbi.nlm.nih.gov/pubmed/34441160
http://dx.doi.org/10.3390/e23081020
work_keys_str_mv AT polatomirko propositionalkernels
AT aiollifabio propositionalkernels