On the integration of symbolic and sub-symbolic techniques for XAI: A survey
Roberta Calegari, Giovanni Ciatto, Andrea Omicini
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
Intelligenza Artificiale 14(1), pages 7-32, 26 pages, September 2020.
Matteo Baldoni, Federico Bergenti, Stefania Monica, Giuseppe Vizzari (eds.), IOS Press.
Author = {Calegari, Roberta and Ciatto, Giovanni and Omicini, Andrea},
Editor = {Baldoni, Matteo and Bergenti, Federico and Monica, Stefania and Vizzari, Giuseppe},
Booktitle = {Special Issue for the Twentieth Edition of the Workshop ‘From Objects to Agents’},
Doi = {10.3233/IA-190036},
IrisId = {11585/772707},
ScopusId = {2-s2.0-85092388493},
WosId = {000574865700002},
Journal = {Intelligenza Artificiale},
Keywords = {XAI, symbolic and sub-symbolic AI, explainability, interpretability, trustable system},
Number = 1,
Pages = {7--32},
Publisher = {IOS Press},
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,
Year = 2020}