Syllabus del corso
Titolo
Neural Symbolic Computation
Docente(i)
Guido Fiorino
Rafael Peñaloza
Italo Zoppis
Lingua
Inglese
Breve descrizione
Il corso ha lo scopo di presentare il concetto di integrazione simbolica alle reti neurali (Neural-Symbolic Learning and Reasoning).
Per quanto possibile si cercherà di rendere il corso autocontenuto in particolare circa le nozioni di logica utili a comprendere l'approccio. Programma di massima:
- Ragionamento non monotonico e ASP;
- Fuzzy e Real Logics;
- inserimento ed estrazione di conoscenza dal sistema CLIP;
- Logic Tensor Networks e, se possibile, Logical Neural Networks;
- Computational Graphs.
Riferimenti:
Un riferimento circa il mondo dell'approccio neuro-simbolico è il seguente:
Pascal Hitzler, Md Kamruzzaman Sarker (eds.), Neuro-Symbolic Artificial Intelligence - The State of the Art. Frontiers in Artificial Intelligence and Applications Vol 342, IOS Press, Amsterdam, 2022.
CFU / Ore
2 CFU/16 ore
Periodo di erogazione
Settembre 2024
Title
Neural Symbolic Computation
Teacher(s)
Guido Fiorino
Rafael Peñaloza
Italo Zoppis
Language
English
Short description
The aim of the course is to present the field of neuro-symbolic integration, also known as
Neural-Symbolic Learning and Reasoning.
As far as possible we try to keep the couse self-contained, in particular for the logical notions necessary to understand the approach.
Tentative programme:
- Non-monotonic reasoning and ASP;
- Fuzzy and Real Logics;
- Inserting and extracting knowledge from CLIP System;
- Logic Tensor Networks and, if possible, Logical Neural Networks;
- Computational Graphs.
References:
a recent book about neuro-symbolic integration:
Pascal Hitzler, Md Kamruzzaman Sarker (eds.), Neuro-Symbolic Artificial Intelligence - The State of the Art. Frontiers in Artificial Intelligence and Applications Vol 342, IOS Press, Amsterdam, 2022.
CFU / Hours
2 CFU/16 Hours
Teaching period
September 2024