Title: Bias in AI-systems: A multi-step approach.
Date & Time: 30 March 2021, 16:00 CET (10:00 EST).
Abstract:
Algorithmic-based decision making powered via AI and (big) data has already penetrated into almostall spheres of human life, from content recommendation and healthcare to predictive policing andautonomous driving, deeply affecting everyone, anywhere, anytime. While technology allows previouslyunthinkable optimizations in the automation of expensive human decision making, the risks that thetechnology can pose are also high, leading to an ever increasing public concern about the impact of thetechnology in our lives. The area of responsible AI has recently emerged in an attempt to put humansat the center of AI-based systems by considering aspects, such as fairness, reliability and privacy ofdecision-making systems.In this talk, we will focus on the fairness aspect. We will start with understanding the many sources ofbias and how biases can enter at each step of the learning process and even get propagated/amplifiedfrom previous steps. We will continue with methods for mitigating bias which typically focus on somestep of the pipeline (data, algorithms or results) and why it is important to target bias in each stepand collectively, in the whole (machine) learning pipeline. We will conclude this talk by discussingaccountability issues in connection to bias and in particular, proactive consideration via bias-aware datacollection, processing and algorithmic selection and retroactive consideration via explanations.
Speaker’s Bio:
Eirini Ntoutsi is since March 2021 full Professor of Artificial Intelligence at the Free University (FU) Berlin. Prior to joining FU, she was an Associate Professor of Intelligent Systems at the Leibniz University of Hanover (LUH), Germany. Prior to that, she was a post-doctoral researcher at the Ludwig-Maximilians-University (LMU) in Munich, Germany in the group of Prof. H.-P. Kriegel. She joined the group as a post-doctoral fellow of the Alexander von Humboldt Foundation. She holds a PhD in Data Mining from the University of Piraeus, Greece and a master and diploma in Computer Engineering and Informatics from the University of Patras, Greece. Her research interests lie in the fields of Artificial Intelligence (AI) and Machine Learning (ML) and can be summarized as developing methods for i) learning over complex data and data streams, covering aspects such as adaptive learning, change detection and stability as well as ii) responsible AI, covering aspects such as fairness-aware learning, data quality and proper evaluation of AI/ML methods. Her research is supported by prestigious funding bodies, including the European Commission, the German Research Foundation (DFG), the Volkswagen Foundation etc. She serves on several boards and organizing committees including the ACM Intl Conference on Information and Knowledge Management (CIKM 2020) as demo and posters co-chair, the IEEE International Conference on Data Mining (ICDM 2017) as publicity co-chair and the German Machine Learning and Data Mining community meeting (KDML 2019) as program co-chair. She serves in the technical committee of many international conferences and she is a frequently reviewer for a number of international technical journals.
===========================================================================
The Association for AI in Science and Industry (www.aaisi.org).
The AI Colloquium -Invited Speech.
Participation is FREE and OPEN to all.
Prior REGISTRATION is required.
Registration Deadline: March 29, 2021.
Registration Link: To be announced.
===========================================================================
