Select a calendar:
Filter November Events by Event Type:
Events for the 5th week of November
-
PTE Webinar
Mon, Nov 30, 2020 @ 01:00 PM - 02:00 PM
Mork Family Department of Chemical Engineering and Materials Science
Workshops & Infosessions
An Innovative laboratory Method to Measure Stress-dependent Source Rock Permeability
by
Dr. Hui-Hai Liu
Aramco Research Center, Houston, Texas
More Information: Nov 30 Webinar.jpg
Location: ZOOM
WebCast Link: zoom 991 9385 9401 Passcode: 627961
Audiences: Everyone Is Invited
Contact: iraj ershaghi
-
DEN@Viterbi - Online Graduate Engineering Virtual Information Session
Wed, Dec 02, 2020 @ 09:00 AM - 10:00 AM
DEN@Viterbi, Viterbi School of Engineering Graduate Admission
Workshops & Infosessions
Join USC Viterbi School of Engineering for a virtual information session via WebEx, providing an introduction to DEN@Viterbi, our top ranked online delivery system. Discover the 40+ graduate engineering and computer science programs available entirely online.
Attendees will have the opportunity to connect directly with USC Viterbi representatives during the session to discuss the admission process, program details and the benefits of online delivery for the working professional.
Register Today!WebCast Link: https://uscviterbi.webex.com/uscviterbi/onstage/g.php?MTID=e63e172b3f7e9e6edee19befc0382679b
Audiences: Everyone Is Invited
Contact: Corporate & Professional Programs
-
Computer Science General Faculty Meeting
Wed, Dec 02, 2020 @ 10:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Receptions & Special Events
Bi-Weekly regular faculty meeting for invited full-time Computer Science faculty only. Event details emailed directly to attendees.
Location: Zoom Meeting
Audiences: Invited Faculty Only
Contact: Assistant to CS chair
-
DEN@Viterbi - Online Graduate Engineering Virtual Information Session
Wed, Dec 02, 2020 @ 06:00 PM - 07:00 PM
DEN@Viterbi, Viterbi School of Engineering Graduate Admission
Workshops & Infosessions
Join USC Viterbi School of Engineering for a virtual information session via WebEx, providing an introduction to DEN@Viterbi, our top ranked online delivery system. Discover the 40+ graduate engineering and computer science programs available entirely online.
Attendees will have the opportunity to connect directly with USC Viterbi representatives during the session to discuss the admission process, program details and the benefits of online delivery for the working professional.
Register Today!WebCast Link: https://uscviterbi.webex.com/uscviterbi/onstage/g.php?MTID=eed9fdaeab54aae14408ad62ae513404e
Audiences: Everyone Is Invited
Contact: Corporate & Professional Programs
-
NLSeminar-INFORMATION-THEORETIC PROBING WITH MINIMUM DESCRIPTION LENGTH
Thu, Dec 03, 2020 @ 10:00 AM - 11:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Elena Voita, Univ of Edinburgh
Talk Title: INFORMATION-THEORETIC PROBING WITH MINIMUM DESCRIPTION LENGTH
Abstract: How can you know whether a model has learned to encode a linguistic property? The most popular approach to measure how well pretrained representations encode a linguistic property is to use the accuracy of a probing classifier (probe). However, such probes often fail to adequately reflect differences in representations, and they can show different results depending on probe hyperparameters. As an alternative to standard probing, we propose information-theoretic probing which measures minimum description length MDL of labels given representations. In addition to probe quality, the description length evaluates the amount of effort needed to achieve this quality. We show that 1 MDL can be easily evaluated on top of standard probe training pipelines, and 2 compared to standard probes, the results of MDL probing are more informative, stable, and sensible.
Biography: Elena Voita is a Ph.D. student at the University of Edinburgh and University of Amsterdam supervised by Ivan Titov and Rico Sennrich, and is currently a Facebook PhD Fellow. Her research focuses on document level neural machine translation, as well as on understanding what and how neural models learn. Previously, she was a research scientist at Yandex Research and worked closely with the Yandex Translate team. She also teaches NLP at the Yandex School of Data Analysis.
Host: Jon May and Mozhdeh Gheini
More Info: https://nlg.isi.edu/nl-seminar/
Webcast: https://usc.zoom.us/j/96662265166Location: Information Science Institute (ISI) - Virtual Only
WebCast Link: https://usc.zoom.us/j/96662265166
Audiences: Everyone Is Invited
Contact: Petet Zamar
Event Link: https://nlg.isi.edu/nl-seminar/