Neuro-symbolic Computation for XAI: Towards a Unified Model

Last modified by Andrea Omicini on 01/05/2021 16:48

Giuseppe Pisano, Giovanni Ciatto, Roberta Calegari, Andrea Omicini

The idea of integrating symbolic and sub-symbolic approaches to make intelligent systems (IS) understandable and explainable is at the core of new fields such as neuro-symbolic computing (NSC). This work lays under the umbrella of NSC, and aims at a twofold objective. First, we present a set of guidelines aimed at building explainable IS, which leverage on logic induction and constraints to integrate symbolic and sub-symbolic approaches. Then, we reify the proposed guidelines into a case study to show their effectiveness and potential, presenting a prototype built on the top of some NSC technologies.

(keywords) XAI, Hybrid Systems, Neural Networks, Logical Constraining
WOA 2020 – 21th Workshop “From Objects to Agents", CEUR Workshop Proceedings (AI*IA Series) 2706, pages 101–117, October 2020.
Roberta Calegari, Giovanni Ciatto, Enrico Denti, Andrea Omicini, Giovanni Sartor (eds.), Sun SITE Central Europe, RWTH Aachen University, Aachen, Germany
21st Workshop “From Objects to Agents" (WOA 2020), Bologna, Italy, 14–16 September 2020. Proceedings
address = {Aachen, Germany},
author = {Pisano, Giuseppe and Ciatto, Giovanni and Calegari, Roberta and Omicini, Andrea},
booktitle = {WOA 2020 -- 21th Workshop ``From Objects to Agents''},
editor = {Calegari, Roberta and Ciatto, Giovanni and Denti, Enrico and Omicini, Andrea and Sartor, Giovanni},
keywords = {XAI, Hybrid Systems, Neural Networks, Logical Constraining},
iris-id = {11585/781387},
issn = {1613-0073},
location = {Bologna, Italy},
month = oct,
note = {21st Workshop ``From Objects to Agents'' (WOA 2020), Bologna, Italy, 14--16~} # sep # {~2020. Proceedings},
pages = {101--117},
publisher = {Sun SITE Central Europe, RWTH Aachen University},
scopus-id = {2-s2.0-85095616404},
series = {CEUR Workshop Proceedings},
subseries = {AI*IA Series},
title = {Neuro-symbolic Computation for {XAI}: Towards a Unified Model},
url = {},
url-pdf = {},
volume = 2706,
year = 2020}


Publication Data

2011 © aliCE Research Group @ DEIS, Alma Mater Studiorum-Università di Bologna