COOKIES: By using this website you agree that we can place Google Analytics Cookies on your device for performance monitoring. |
University of Cambridge > Talks.cam > Microsoft Research Cambridge, public talks > Hedging Against Uncertainty via Multiple Diverse Predictions
Hedging Against Uncertainty via Multiple Diverse PredictionsAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Microsoft Research Cambridge Talks Admins. This event may be recorded and made available internally or externally via http://research.microsoft.com. Microsoft will own the copyright of any recordings made. If you do not wish to have your image/voice recorded please consider this before attending What does a young child or a high-school student with no knowledge of probability do when faced with a problem whose answer they are uncertain of? They make guesses. Modern machine perception algorithms (for object detection, pose estimation, or semantic scene understanding), despite dealing with tremendous amounts of ambiguity, do not. In this talk, I will describe a line of work in my lab where we have been developing machine perception models that output not just a single-best solution, rather a /diverse/ set of plausible guesses. I will discuss inference in graphical models, connections to submodular maximization over a “doubly-exponential” space, and how/why this achieves state-of-art performance on Pascal VOC 2012 segmentation dataset. Following my own advice, I will talk about talk some other cool things as well (including deep learning of course). This talk is part of the Microsoft Research Cambridge, public talks series. This talk is included in these lists:
Note that ex-directory lists are not shown. |
Other listsRECOUP open seminar series The Audrey Richards Annual Lecture in African Studies Cambridge Finance Workshop Series Making Refuge: Creative Responses to the Refugee Crisis Inner Space, The Meditation Centre EED Film Series: 'Waiting for Superman'Other talksAdrian Seminar: Ensemble coding in amygdala circuits Rhys Jones: Temporal Claustrophobia at the Continental Congress, 1774-1776 Intrinsically Motivating Teachers;STIR's use of Data Driven Insight to Iterate, Pivot and (where necessary) Fail Fast Changing understandings of the human fetus over five decades of legal abortion Handbuchwissenschaft, or: how big books maintain knowledge in the twentieth-century life sciences |