Roberta Calegari, Giovanni Ciatto, Enrico Denti, Andrea Omicini, Giovanni Sartor (a cura di)
WOA 2020 – 21th Workshop “From Objects to Agents", pp. 101–117
CEUR Workshop Proceedings (AI*IA Series) 2706
Sun SITE Central Europe, RWTH Aachen University, Aachen, Germany
ottobre 2020
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.
parole chiave
XAI, Hybrid Systems, Neural Networks, Logical Constraining
presentazione di riferimento
evento origine
rivista o collana
pubblicazione contenitore
funge da
pubblicazione di riferimento per presentazione
Neuro-symbolic Computation for XAI: Towards a Unified Model (WOA 2020, 15/09/2020) — Giuseppe Pisano (Giovanni Ciatto, Giuseppe Pisano, Roberta Calegari, Andrea Omicini)
CEUR Workshop Proceedings (CEUR-WS.org)
WOA 2020 – 21st Workshop “From Objects to Agents” (curatela, 2020) — Roberta Calegari, Giovanni Ciatto, Enrico Denti, Andrea Omicini, Giovanni Sartor