In this paper we sketch a vision of explainability of intelligent systems as a logic approach suitable to be injected into and exploited by the system actors once integrated with sub-symbolic techniques. In particular, we show how argumentation could be combined with different extensions of logic programming – namely, abduction, inductive logic programming, and probabilistic logic programming – to address the issues of explainable AI as well as some ethical concerns about AI.
Explainable and Ethical AI: A Perspective on Argumentation and Logic Programming / Roberta Calegari, Andrea Omicini, Giovanni Sartor. - STAMPA. - 12414:(2021), pp. 19-36. (Intervento presentato al convegno The 19th International Conference of the Italian Association for Artificial Intelligence (AIxIA 2020) tenutosi a Virtual Event nel 25–27 November 2020) [10.1007/978-3-030-77091-4_2].
Explainable and Ethical AI: A Perspective on Argumentation and Logic Programming
Roberta Calegari;Andrea Omicini;Giovanni Sartor
2021
Abstract
In this paper we sketch a vision of explainability of intelligent systems as a logic approach suitable to be injected into and exploited by the system actors once integrated with sub-symbolic techniques. In particular, we show how argumentation could be combined with different extensions of logic programming – namely, abduction, inductive logic programming, and probabilistic logic programming – to address the issues of explainable AI as well as some ethical concerns about AI.| File | Dimensione | Formato | |
|---|---|---|---|
|
COS-AIIA2020.pdf
accesso aperto
Tipo:
Postprint
Licenza:
Licenza per accesso libero gratuito
Dimensione
715.13 kB
Formato
Adobe PDF
|
715.13 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
