Explaining with argumentationIt

Abstract: Explaining  with argumentationIt is widely acknowledged that transparency of automated decision making is crucial for deployability of intelligent systems, and explaining the reasons why some outputs are computed  is a way to achieve this transparency. The form that explanations should take, however, is much less clear. In this talk I will explore two classes of explanations, which I call 'lean' and 'mechanistic': the former focus on the inputs contributing to decisions given in output; the latter reflect instead the internal functioning of the  automated decision making fed with the inputs and computing those outputs. I will show how both classes of explanations can be supported by forms of computational argumentation, and will describe forms of argumentative XAI in several settings, including multi-attribute decision making and machine learning.

Link for on-line participation: 

https://teams.microsoft.com/l/meetup-join/19%3aV0oVUvttECrk8ErVdnBlqju0VxsLpE-H0mLI1Uyimyg1%40thread.tacv2/1639492975456?context=%7b%22Tid%22%3a%2260240b54-f639-46a1-bf85-a1aba95550fe%22%2c%22Oid%22%3a%22545c65bc-8cd7-48c5-96c8-ec60d82ad28f%22%7d

I seminari si terranno sia in modalità blended. Gli utenti esterni che vorranno partecipare in presenza sono invitati a inviare all'indirizzo classi@sns.it un messaggio entro le ore 14:00 di Martedì 8 febbraio 2022.