BEGIN:VCALENDAR
VERSION:2.0
METHOD:PUBLISH
CALSCALE:GREGORIAN
PRODID:-//WordPress - MECv7.34.1//EN
X-ORIGINAL-URL:https://datasciences.utoronto.ca/
X-WR-CALNAME:DSI
X-WR-CALDESC:A hub for data science activity at the University of Toronto.
X-WR-TIMEZONE:America/Toronto
BEGIN:VTIMEZONE
TZID:America/Toronto
X-LIC-LOCATION:America/Toronto
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20260308T030000
RRULE:FREQ=YEARLY;BYMONTH=03;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20261101T010000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-PUBLISHED-TTL:PT1H
X-MS-OLK-FORCEINSPECTOROPEN:TRUE
BEGIN:VEVENT
CLASS:PUBLIC
UID:MEC-1dec69fd432365f7affe596a50965e29@datasciences.utoronto.ca
DTSTART;TZID=America/Toronto:20220425T171500
DTEND;TZID=America/Toronto:20220425T181500
DTSTAMP:20220401T105320Z
CREATED:20220401
LAST-MODIFIED:20220805
PRIORITY:5
SEQUENCE:0
TRANSP:OPAQUE
SUMMARY:Data Sciences Speaker Series at UofT: Dustin Tran
DESCRIPTION:Join us for the next installment of the Data Science Speaker Series at U of T with Dr. Dustin Tran, Research Scientist at Google Brain!\n \nFree Event | Registration Required\n\nDate: Apr 25, 2022\nTime: 5:15 pm – 6:15 pm\n\nTalk Title: Reliability for Deep Learning\n \nAbstract: Deep learning models are bad at signalling failure: They can make predictions with high confidence, and this is problematic in real-world applications such as healthcare, self-driving cars, and natural language systems, where there are considerable safety implications, or where there are discrepancies between the training data and data that the model makes predictions on. There is a pressing need both for understanding when models should not make predictions and to improve model robustness to natural changes in the data. We’ll give an overview of this problem set. We also highlight promising avenues from recent work, including methods that average over multiple neural network predictions such as Bayesian neural nets and ensembles; as well as the use of large pre-trained models.\n \nSpeaker Profile: Dustin is a research scientist at Google Brain. His research contributions examine the intersection of probability and deep learning, particularly in the areas of probabilistic programming, variational inference, giant models, and Bayesian neural networks. He completed his Ph.D. at Columbia under David Blei. He’s received awards such as the John M. Chambers Statistical Software award and the Google Ph.D. Fellowship in Machine Learning. He served as Area Chair at NeurIPS, ICML, ICLR, IJCAI, and AISTATS and organized “Approximate Inference” and “Uncertainty & Robustness” workshops at NeurIPS and UAI.\n
URL:https://datasciences.utoronto.ca/event/data-sciences-speaker-series-at-uoft-dustin-tran/
CATEGORIES:Data Sciences Institute,Data Sciences Speaker Series,DSSS@ U of T - 2021-2022 Season,DSSS@U of T
LOCATION:Online (Zoom)
ATTACH;FMTTYPE=image/jpeg:https://datasciences.utoronto.ca/wp-content/uploads/2022/04/DustinTran-DSSS.jpg
END:VEVENT
END:VCALENDAR