The Human-Computer Interaction (HCI) community has long stressed the need for a more user-centered approach to Explainable Artificial Intelligence (XAI), a research area that aims at defining algorithms and tools to illustrate the predictions of the so-called black-box models. This approach can benefit from the fields of user-interface, user experience, and visual analytics. In this demo, we propose a visual-based tool, "F.I.P.E.R.", that shows interactive explanations combining rules and feature importance.
Demo: an interactive visualization combining rule-based and feature importance explanations
Cappuccio E;Fadda D;Rinzivillo S
2023
Abstract
The Human-Computer Interaction (HCI) community has long stressed the need for a more user-centered approach to Explainable Artificial Intelligence (XAI), a research area that aims at defining algorithms and tools to illustrate the predictions of the so-called black-box models. This approach can benefit from the fields of user-interface, user experience, and visual analytics. In this demo, we propose a visual-based tool, "F.I.P.E.R.", that shows interactive explanations combining rules and feature importance.File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
prod_486658-doc_201970.pdf
solo utenti autorizzati
Descrizione: Demo: an Interactive Visualization Combining Rule-Based and Feature Importance Explanations
Tipologia:
Versione Editoriale (PDF)
Dimensione
1.29 MB
Formato
Adobe PDF
|
1.29 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
|
prod_486658-doc_202081.pdf
accesso aperto
Descrizione: Postprint - Demo: an Interactive Visualization Combining Rule-Based and Feature Importance Explanations
Tipologia:
Versione Editoriale (PDF)
Dimensione
1.29 MB
Formato
Adobe PDF
|
1.29 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
