Logic Programming library for Machine Learning: API design and prototype


Giovanni Ciatto, Matteo Castigliò, Roberta Calegari

Proceedings of the  37th Italian Conference on Computational Logic
 2022

In this paper we address the problem of hybridising logic and sub-symbolic approaches to artificial intelligence, following the purpose of creating flexible and data-driven systems, which are simultaneously comprehensible and capable of automated learning. In particular, in this paper we propose a logic API for supervised machine learning, enabling logic programmers to exploit neural networks – among the others – in their programs. Accordingly, we discuss the design and architecture of a library reifying our API for the Prolog language, on top of the 2P-Kt logic ecosystem. Finally, we discuss a number of snippets aimed at exemplifying the major benefits of our approach when it comes to design hybrid systems.

(keywords) logic programming, machine learning, API, 2P-Kt

Events

  • 37th Italian Conference on Computational Logic (CILC 2022) — 29/06/2022–01/07/2022

Tags:

Publication

— authors

Giovanni Ciatto, Matteo Castigliò, Roberta Calegari

— status

accepted

— sort

paper in proceedings

Venue

— volume

Proceedings of the  37th Italian Conference on Computational Logic

— publication date

2022

URLs

original page

BibTeX

— BibTeX ID
LogicApi4MlCilc2022
— BibTeX category
inproceedings

Partita IVA: 01131710376 - Copyright © 2008-2022 APICe@DISI Research Group - PRIVACY