The inaugural BEWARE workshop and its sequel, BEWARE-23, are discussed in detail, including their focus on themes such as Bias, Risk, Explainability, and the influence of Logic in AI. A novel tool developed by BRIO and Alkemy for post-hoc analysis of AI classifiers, aimed at exposing potential biases, is also discussed. This article emphasizes the need for ongoing scrutiny, evaluation, and ethical consideration in the development and application of AI technologies, underlining BRIO’s commitment to advancing the field in an ethical, fair, and accessible manner.
Dissemination Corner: BRIO (2023)
Fabio Aurelio D'Asaro
2023-01-01
Abstract
The inaugural BEWARE workshop and its sequel, BEWARE-23, are discussed in detail, including their focus on themes such as Bias, Risk, Explainability, and the influence of Logic in AI. A novel tool developed by BRIO and Alkemy for post-hoc analysis of AI classifiers, aimed at exposing potential biases, is also discussed. This article emphasizes the need for ongoing scrutiny, evaluation, and ethical consideration in the development and application of AI technologies, underlining BRIO’s commitment to advancing the field in an ethical, fair, and accessible manner.
File in questo prodotto:
| File | Dimensione | Formato | |
|---|---|---|---|
|
TheReasoner-2.pdf
accesso aperto
Licenza:
Creative commons
Dimensione
5.82 MB
Formato
Adobe PDF
|
5.82 MB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
