Tutorial on Explanations in Interactive Machine Learning @ AAAI-22

Recording of the AAAI-22 Tutorial on Explanations in Interactive Machine Learning. Slides: https://sites.google.com/view/aaai22-ximl-tutorial/home 00:00 Motivation and Challenges - Öznur Alkan (Optum-United Health Group) 14:42 Interacting via Local Explanations - Stefano Teso (University of Trento) 36:47 Interacting via Rule-based Explanations - Elizabeth Daly (IBM Research Ireland) 58:34 Interacting via Concept-based Explanations - Wolfgang Stammer (TU Darmstadt) Description: This tutorial is intended for Artificial Intelligence researchers and practitioners, as well as domain experts interested in human-in-the-loop machine learning, including interactive recommendation and active learning. The participants will gain an understanding of current developments in interactive machine learning from rich human feedback – with an emphasis on white-box interaction and explanation-guided learning – as well as a conceptual map of the variety of methods available and of the relationships between them. The main goal is to inform the audience about the state-of-the-art in explanations for interactive machine learning, open issues and research directions, and how these developments relate to the broader context of machine learning and AI.