Share:

Juan M. Durán (Delft University of Technology): “Trust and Justification in AI: On the Role of Computational Reliabilism”

April 3rd at 17:00. Room: Aula Alpha, ground floor of the Polimi building 24 (via Golgi 40). 

Abstract: In this talk, I aim to explore the significance of trust and justification in machine learning (ML). To begin, I’ll briefly touch upon two promising epistemologies for ML — transparency and computational reliabilism (CR). However, my focus will be on defending the latter, requiring a more in-depth discussion. I’ll dedicate some time to elucidate how CR operates, and which assumptions are built-in. Next, I plan to illustrate how CR works in the context of Forensic ML. Lastly, I’ll address two objections against CR: i) the concern that, under CR, statistically insignificant yet serious errors can compromise the reliability of AI algorithms; and ii) the argument that CR, being a reliabilist epistemology, demands a high frequency of success, ultimately posing an issue of high predictive accuracy. I’ll present arguments to counter these objections, advocating for computational reliabilism as a promising epistemology for ML.

Share:

Read more:

Date: 27th November 2024 Time: 9:00 AM Venue: Sala Consiglio, VII Floor, Mathematics Department, Politecnico di Milano (Leonardo Campus) The ...

Date: 25-26 November 2024 Time: Venue: Sala Consiglio, VII Floor, Dipartimento di Matematica, Politecnico di Milano (Leonardo) Analogies in physics ...

No more post to discover.
More from Events Meta Lectures:
Highlights: