All times are given in UTC+2. The program spans two days: Monday morning, September 18th, and Friday morning, September 22nd.<\/p>\n
Monday Morning (PoliTo Room 12i):<\/strong> Friday Morning (PoliTo Room 8i):<\/strong> All times are given in UTC+2. The program spans two days: Monday morning, September 18th, and Friday morning, September 22nd. Monday Morning (PoliTo Room 12i): 9:00am – 9:15am: Welcome and introduction 9:15am – 10:30am: Invited talk by Mihaela van der Schaar, Professor of Machine Learning, Artificial Intelligence and Medicine at\u2026<\/p>\n
\n9:00am – 9:15am<\/strong>: Welcome and introduction
\n9:15am – 10:30am<\/strong>: Invited talk by Mihaela van der Schaar, Professor of Machine Learning, Artificial Intelligence and Medicine at the University of Cambridge and a Fellow at The Alan Turing Institute in London
\nTitle of the talk:<\/strong> Turning the lights on inside the black box: New frontiers in machine learning interpretability from time-series to causal inference to unsupervised learning
\n10:30am – 11:00am<\/strong>: First session of presentations
\n– 10:30<\/strong>am<\/strong>: An Efficient Shapley Value Computation for the Naive Bayes Classifier [Slides<\/a>] [Paper<\/a>]
\n– 10:45am<\/strong>: Predicate-based explanation of a Reinforcement Learning agent via action importance evaluation [Slides<\/a>] [Paper<\/a>]
\n11:00am – 11:30am<\/strong>: Coffee break
\n11:30am – 12:30pm<\/strong>: Second session of presentations
\n– 11:30am<\/strong>: Revealing Similar Semantics Inside CNNs: An Interpretable Concept-based Comparison of Feature Spaces [Slides<\/a>] [Paper<\/a>]
\n– 11:45am<\/strong>: An Experimental Investigation into the Evaluation of Explainability Methods for Computer Vision
\n– 12:00pm<\/strong>: Natively Interpretable t-SNE [Slides<\/a>] [Paper<\/a>]
\n12:15pm<\/strong>: Feedback from workshop participants<\/p>\n
\n9:00am – 11:00am<\/strong>: Introduction and Tutorial on Explainable Graph ML<\/strong><\/a>: Part 1
\n11:00am – 11:15am<\/strong>: Coffee break
\n11:15am – 12:00pm<\/strong>: Tutorial: Part 2
\n12:00pm – 12:15pm<\/strong>: Feedback and discussion
\n12:15pm – 13:00pm<\/strong>: Third session of presentations
\n– 12:15pm<\/strong>: On the Adaptability of Attention-Based Interpretability in Different Transformer Architectures for Multi-Class Classification Tasks [Slides<\/a>] [Paper<\/a>]
\n– 12:30pm<\/strong>: Analyzing the Explanation and Interpretation Potential of Matrix Capsule Networks [Slides<\/a>] [Paper<\/a>]
\n– 12:45pm<\/strong>: Local interpretability of random forests for multi-target regression [Slides<\/a>] [Paper<\/a>]
\n13:00pm<\/strong>: Closing<\/p>\n","protected":false},"excerpt":{"rendered":"