On the integration of symbolic and sub-symbolic techniques for XAI: A survey


Roberta Calegari, Giovanni Ciatto, Andrea Omicini

Intelligenza Artificiale 14(1), pp. 7-32, 26 pagine, settembre 2020
IOS Press
Matteo Baldoni, Federico Bergenti, Stefania Monica, Giuseppe Vizzari (a cura di)
Special Issue for the Twentieth Edition of the Workshop ‘From Objects to Agents’

The more intelligent systems based on sub-symbolic techniques pervade our everyday lives, the less human can understand them. This is why symbolic approaches are getting more and more attention in the general effort to make AI interpretable, explainable, and trustable. Understanding the current state of the art of AI techniques integrating symbolic and sub-symbolic approaches is then of paramount importance, nowadays—in particular in the XAI perspective. This is why this paper provides an overview of the main symbolic/sub-symbolic integration techniques, focussing in particular on those targeting explainable AI systems.

(keywords) XAI, symbolic and sub-symbolic AI, explainability, interpretability, trustable system
 @article{xaisurvey-ia14,
author = {Calegari, Roberta and Ciatto, Giovanni and Omicini, Andrea},
booktitle = {Special Issue for the Twentieth Edition of the Workshop `From Objects to Agents'},
dblpid = {journals/ia/CalegariCO20},
doi = {10.3233/IA-190036},
editor = {Baldoni, Matteo and Bergenti, Federico and Monica, Stefania and Vizzari, Giuseppe},
irisid = {11585/772707},
journal = {Intelligenza Artificiale},
keywords = {XAI, symbolic and sub-symbolic AI, explainability, interpretability, trustable system},
number = 1,
pages = {7--32},
publisher = {IOS Press},
scopusid = {2-s2.0-85092388493},
title = {On the integration of symbolic and sub-symbolic techniques for {XAI}: A survey},
url = {http://content.iospress.com/articles/intelligenza-artificiale/ia190036},
volume = 14,
wosid = {000574865700002},
year = 2020

Riviste & collane

Eventi

  • XX Workshop "From Objects to Agents" (WOA 2019) — 26/06/2019–28/06/2019

Pubblicazione

— autori/autrici

Roberta Calegari, Giovanni Ciatto, Andrea Omicini

— a cura di

Matteo Baldoni, Federico Bergenti, Stefania Monica, Giuseppe Vizzari

— stato

pubblicato

— tipo

articolo su rivista

Sede di pubblicazione

— rivista

Intelligenza Artificiale

— volume

14

— numero

1

— pagine

7-32

— data di pubblicazione

settembre 2020

URL

pagina originale

Identificatori

— DOI

10.3233/IA-190036

— DBLP

journals/ia/CalegariCO20

— IRIS

11585/772707

— Scopus

2-s2.0-85092388493

— WoS / ISI

000574865700002

BibTeX

— BibTeX ID
xaisurvey-ia14
— BibTeX category
article

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