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


pagemagnifierBibTeX_logo.pngmagnifierpage_white_acrobatmagnifier

Roberta Calegari, Giovanni Ciatto, Andrea Omicini

Intelligenza Artificiale 14(1), pages 7–32
September 2020

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

Special Issue for the Twentieth Edition of the Workshop ‘From Objects to Agents’

Journals & Series

Events

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

Publication

— authors

— editors

Matteo Baldoni, Federico Bergenti, Stefania Monica, Giuseppe Vizzari

— status

published

— sort

article in journal

— publication date

September 2020

— journal

Intelligenza Artificiale

— volume

14

— issue

1

— pages

7–32

— number of pages

26

URLs

original page

identifiers

— DOI

10.3233/IA-190036

— DBLP

journals/ia/CalegariCO20

— IRIS

11585/772707

— Scopus

2-s2.0-85092388493

— WoS / ISI

000574865700002

notes

— note

Special Issue for the Twentieth Edition of the Workshop ‘From Objects to Agents’

Partita IVA: 01131710376 — Copyright © 2008–2023 APICe@DISI – PRIVACY