Speaker: Mark Keane (Chair of Computer Science at University College Dublin)
Location:
Join Zoom Meeting https://uio.zoom.us/j/69426798457?pwd=L2dFVVB0a20vL2l4YzdWZk15bERIQT09
Meeting ID: 694 2679 8457
Passcode: 351603
Title: Explaining Artificial Intelligence: Contrastive Explanations for AI Black Boxes and What People Think of Them
Summary: In recent years, there has been a lot of excitement around the apparent success of Deep Learning in AI. There has also been a decent amount of skepticism around the issue of knowing what these models are actually doing, when they are being successful. This has led to the emerging area of Explainable AI, where techniques have been developed to explain a model’s workings to end-users and model developers. Recently, contrastive explanations (counterfactual and semi-factual) have become very popular for explaining the predictions of such black-box AI systems. For example, if you are refused a loan by an AI and ask “why”, a counterfactual explanation might tell you, “well, if you asked for a smaller loan, then you would have been granted the loan.”. These counterfactuals are generated by methods that perform perturbations of the feature values of the original situation (e.g., we perturb the value of the loan). In this talk, I review some of the contrastive methods we have developed for different datasets (tabular, image, time-series) using on a case-based approach. I also review some of our very recent work on user studies testing whether these AI methods are comprehendible to users in the ways that are assumed by AI researchers (Spoiler Alert: they often aren’t).
About the speaker: Since 1998, Prof. Mark Keane has been Chair of Computer Science at University College Dublin. From 2004-2007 he was Director of ICT (2004-2006) and Director General (2006-2007) at Science Foundation Ireland (SFI) where he oversaw a 700M+ euro research investment. He advised the Irish Government on its €3.7B Strategy for Science, Technology & Innovation (SSTI). He was also VP of Innovation & Partnerships at UCD (2007-2009). He has a BA (UCD) and PhD (TCD) in Cognitive Psychology and previously worked in University of London, the Open University, Cardiff University and Trinity College Dublin (FTCD, 1994). Prof. Keane has published 200+ articles, including 20+ books. Keane is a PI in the Insight SFI Centre for Data Analytics and VistaMilk SFI Centre. His work in Cognitive Science is concerned with how people manage to produce new ideas from old knowledge (using analogy, concept combination, metaphor) and how they deal with things they don't know or expect (surprise, unexpectedness). In Artificial Intelligence, he works on case-based reasoning, machine learning and explainable AI. He is currently a PI in the Insight SFI Centre for Data Analytics and the VistaMilk SFI Research Centre for precision agriculture.
