In the context of the Internet of Things (IoT), intelligent systems (IS) are increasingly relying on Machine Learning (ML) techniques. Given the opaqueness of most ML techniques, however, humans have to rely on their intuition to fully understand the IS outcomes: helping them is the target of eXplainable Artificial Intelligence (XAI). Current solutions – mostly too specific, and simply aimed at making ML easier to interpret – cannot satisfy the needs of IoT, characterised by heterogeneous stimuli, devices, and data-types concurring in the composition of complex information structures. Moreover, Multi-Agent Systems (MAS) achievements and advancements are most often ignored, even when they could bring about key features like explainability and trustworthiness. Accordingly, in this paper we (i) elicit and discuss the most significant issues affecting modern IS, and (ii) devise the main elements and related interconnections paving the way towards reconciling interpretable and explainable IS using MAS.

Towards XMAS: eXplainability through Multi-Agent Systems

Giovanni Ciatto;Roberta Calegari;Andrea Omicini;
2019

Abstract

In the context of the Internet of Things (IoT), intelligent systems (IS) are increasingly relying on Machine Learning (ML) techniques. Given the opaqueness of most ML techniques, however, humans have to rely on their intuition to fully understand the IS outcomes: helping them is the target of eXplainable Artificial Intelligence (XAI). Current solutions – mostly too specific, and simply aimed at making ML easier to interpret – cannot satisfy the needs of IoT, characterised by heterogeneous stimuli, devices, and data-types concurring in the composition of complex information structures. Moreover, Multi-Agent Systems (MAS) achievements and advancements are most often ignored, even when they could bring about key features like explainability and trustworthiness. Accordingly, in this paper we (i) elicit and discuss the most significant issues affecting modern IS, and (ii) devise the main elements and related interconnections paving the way towards reconciling interpretable and explainable IS using MAS.
AI&IoT 2019 – Artificial Intelligence and Internet of Things 2019
40
53
Giovanni Ciatto, Roberta Calegari, Andrea Omicini, Davide Calvaresi
File in questo prodotto:
File Dimensione Formato  
paper3.pdf

accesso aperto

Descrizione: PDF editoriale
Tipo: Versione (PDF) editoriale
Licenza: Licenza per Accesso Aperto. Creative Commons Attribuzione (CCBY)
Dimensione 623 kB
Formato Adobe PDF
623 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/707345
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 12
  • ???jsp.display-item.citation.isi??? ND
social impact