Timetable for the TrustML YSS online seminars from May to Jun., 2022. Time (JST)Time (Your Browser)TitleSpeaker Video Link 10:00-11:00 03/05/2022 Learning to Generate Data by Estimating Gradients of the Data Distribution:Yang Song (Stanford University) Video 11:00-12:00 03/05/2022 Towards Trustworthy Machine Learning – From Robustness to Fairness:Boyu Wang (University of Western Ontario) Video 15:00-16:00 10/05/2022 Deconstructing Distributions: A Pointwise Framework of Learning:Gal Kaplun (Harvard University) Video 17:00-18:00 25/05/2022 How to learn powerful two-sample tests:Jonas Kübler (IMPRS-IS) Video 10:00-11:00 31/05/2022 Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary:Takashi Ishida (The University of Tokyo) Video 11:00-12:00 31/05/2022 Adversarial attacks towards audio recognition systems:Yuxuan Chen (Shandong University) Video 10:00-11:00 02/06/2022 Debuggable deep networks:Eric Wong (MIT) Video 17:00-18:00 20/06/2022 Noisy Correspondences: A New Paradigm for Learning with Noisy Labels:Mouxing Yang (Sichuan Univerisity) Video 16:00-17:00 21/06/2022 Partial success in closing the gap between human and machine vision:Robert Geirhos (University of Tübingen) Video 16:00-17:00 27/06/2022 Deep Learning Through the Lens of Example Difficulty:Robert Baldock (Aleph Alpha) No video