BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//INPA - ECPv6.8.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://inpa.lbl.gov
X-WR-CALDESC:Events for INPA
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:20180311T100000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:20181104T090000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/Los_Angeles:20181109T120000
DTEND;TZID=America/Los_Angeles:20181109T130000
DTSTAMP:20260526T171518
CREATED:20180917T155113Z
LAST-MODIFIED:20181107T200037Z
UID:432-1541764800-1541768400@inpa.lbl.gov
SUMMARY:Douglas Finkbeiner (Harvard) - Making neural net classifiers more robust and explainable: Lessons from Adversarial AI
DESCRIPTION:As deep neural nets achieve ever greater successes\, efforts to break them and learn about their failure modes are also ramping up. Security experts and malicious actors are interested in weaknesses per se\, and we scientists are more interested in what we can learn about robustness to inputs somewhat different from training data. I will give examples of attacks and defenses\, and talk about a measure of credibility at inference time.
URL:https://inpa.lbl.gov/event/douglas-finkbeiner-harvard/
LOCATION:50A-5132- Sessler\, 50A-5132 Sessler Conference Room\, CA
END:VEVENT
END:VCALENDAR