As Machine Learning (ML) systems are increasingly becoming part of user-facing applications, their reliability and robustness are key to building and maintaining trust with users and customers, especially for high-stake domains. While advances in learning are continuously improving model performance on expectation, there is an emergent need for identifying, understanding, and mitigating cases where models may fail in unexpected ways. This session is going to discuss ML reliability and robustness from both a theoretical and empirical perspective. In particular, the session will aim at summarizing important ongoing work that focuses on reliability guarantees but also on how such guarantees translate (or not) to real-world applications. Further, the talks and the panel will aim at discussing (1) properties of ML algorithms that make them more preferable than others from a reliability and robustness lens such as interpretability, consistency, transportability etc. and (2) tooling support that is needed for ML developers to check and build for reliable and robust ML. The discussion will be grounded on real-world applications of ML in vision and language tasks, healthcare, and decision making. Session Lead: Besmira Nushi, Microsoft Speaker: Thomas Dietterich, Oregon State University Talk Title: Anomaly Detection in Machine Learning and Computer Vision Speaker: Ece Kamar, Microsoft Talk Title: AI in the Open World: Discovering Blind Spots of AI Speaker: Suchi Saria, Johns Hopkins University Talk Title: Implementing Safe & Reliable ML: 3 key areas of development Q&A panel with all 3 speakers See more on-demand sessions from Microsoft Research’s Frontiers in Machine Learning 2020 [More]
Causality and Increasing model Reliability: Learning Models that are Safe and Robust to Dataset Shifts Suchi Saria directs the Machine Learning and Healthcare Lab at Johns Hopkins University and is the founding research director of the Malone Center for Engineering in Healthcare. She is interested in enabling new classes of diagnostic and treatment planning techniques for healthcare—tools that use statistical machine learning techniques to tease out subtle information from “messy” observational datasets and provide reliable inferences for individualizing care decisions. —– The Summer School of Machine Learning at Skoltech (SMILES) is an online one-week intensive course about modern statistical machine learning methods. It aims at bringing together the Machine Learning community from the CIS, Central Asia, and the Caucasus regions. SMILES presents topics that are at the core of machine learning research, from fundamentals to the state-of-the-art.
About The Webinar Digital Twin is one of the purpose driven Digital transformation themes to reduce operational costs or innovate with new revenue streams for the manufacturing organizations. If properly strategized & implemented, Digital twins have the potential to become a game changer for the organizations to create sustainable competitive advantage. In this webinar, the speakers simplify the definition of digital twins including the application streams, focus on key problems that digital twins solve for manufacturing organizations, and present a case study from automotive industry for digital twin solution implementation based on their experiences.