BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-CALNAME:AI Seminar: Training Machines to Know What They Don't Know
X-WR-TIMEZONE:Pacific Time (US & Canada)
BEGIN:VEVENT
DTSTAMP:20260914T123416Z
UID:tag:localist.com\,2008:EventInstance_46569904238812
DTSTART:20240531T170000Z
DTEND:20240531T180000Z
DESCRIPTION:Pascal Poupart\, Professor\nDavid R. Cheriton School of Compute
 r Science\nUniversity of Waterloo\n\nAbstractModern machine learning predi
 ctors often suffer from overconfidence.  I will explain why neural predict
 ors with a softmax output layer exhibit arbitrarily high confidence away f
 rom the training data. I will describe a simple modification to the softma
 x layer to prevent this type of overconfidence. I will also describe how p
 roduct-of-expert and mixture-of-expert approximations in Bayesian inferenc
 e can lead to over or under confidence. Finally\, I will describe a simple
  interpolation technique to enhance the calibration of predictions in dist
 ributed machine learning applications including federated learning.\n\nSpe
 aker Biography\nPascal Poupart is a Professor in the David R. Cheriton Sch
 ool of Computer Science at the University of Waterloo (Canada). He is also
  a Canada CIFAR AI Chair at the Vector Institute and a member of the Water
 loo AI Institute. He serves on the advisory board of the NSF AI Institute 
 for Advances in Optimization (2022-present) at Georgia Tech. He served as 
 Research Director and Principal Research Scientist at the Waterloo Boreali
 s AI Research Lab at the Royal Bank of Canada (2018-2020). He also served 
 as scientific advisor for ProNavigator (2017-2019)\, ElementAI (2017-2018)
  and DialPad (2017-2018). His research focuses on the development of algor
 ithms for Machine Learning with application to Natural Language Processing
  and Material Discovery. He is most well-known for his contributions to th
 e development of Reinforcement Learning algorithms. Notable projects that 
 his research team are currently working on include inverse constraint lear
 ning\, mean field RL\, RL foundation models\, Bayesian federated learning\
 , uncertainty quantification\, probabilistic deep learning\, conversationa
 l agents\, transcription error correction\, sport analytics\, adaptive sat
 isfiability and material discovery for CO2 recycling.
GEO:44.567164;-123.278692
LOCATION:Kelley Engineering Center\, 1003
SUMMARY:AI Seminar: Training Machines to Know What They Don't Know
URL;VALUE=URI:https://events.oregonstate.edu/event/ai-seminar-inverse-const
 raint-learning-and-risk-averse-reinforcement-learning-for-safe-ai-8627
CATEGORIES:Lecture or Presentation
END:VEVENT
END:VCALENDAR