BEGIN:VCALENDAR VERSION:2.0 PRODID:-//Drupal iCal API//EN X-WR-CALNAME:Events items teaser X-WR-TIMEZONE:America/Toronto BEGIN:VTIMEZONE TZID:America/Toronto X-LIC-LOCATION:America/Toronto BEGIN:DAYLIGHT TZNAME:EDT TZOFFSETFROM:-0500 TZOFFSETTO:-0400 DTSTART:20210314T070000 END:DAYLIGHT BEGIN:STANDARD TZNAME:EST TZOFFSETFROM:-0400 TZOFFSETTO:-0500 DTSTART:20211107T060000 END:STANDARD END:VTIMEZONE BEGIN:VEVENT UID:683787b856454 DTSTART;TZID=America/Toronto:20220207T113000 SEQUENCE:0 TRANSP:TRANSPARENT DTEND;TZID=America/Toronto:20220207T113000 URL:/computer-science/events/seminar-ai-an-algorithmic- safety-view-of-learning-in-human-centered-domains SUMMARY:Seminar • Artificial Intelligence • An Algorithmic Safety View of\nLearning in Human-centered Domains CLASS:PUBLIC DESCRIPTION:Summary \n\nPLEASE NOTE: THIS SEMINAR WILL BE GIVEN ONLINE.\n\n SHALMALI JOSHI\, POSTDOCTORAL FELLOW\nCenter for Research on Computation a nd Society\, Harvard University\n\nMachine Learning advances have revolut ionized many domains such as\nmachine translation\, complex game playing\, and scientific discovery.\nOn the other hand\, ML has only enjoyed modest successes in\nhuman-centered applications. To improve the utility\, relia bility\, and\nrobustness of Machine Learning (ML) models in human-centered domains\,\nwe need to address several foundational challenges.\n DTSTAMP:20250528T220128Z END:VEVENT END:VCALENDAR