[engine_icon style=”icon-user”] Speaker
Bernhard Schölkopf
Statistical and Causal Learning
[engine_icon style=”icon-calendar”] Date & Time
Thursday, April 25th
@5:00 pm
[engine_icon style=”icon-map-marker”] Place
Courant Institute of Mathematical Sciences
Warren Weaver Hall, Room 109
251 Mercer Street, New York, NY 10012
(photo ID necessary for non-NYU visitors)
Inference of Cause and Effect
Friday, April 26th
@10:00 am
Courant Institute of Mathematical Sciences
Warren Weaver Hall, Room 1302
251 Mercer Street, New York, NY 10012
(photo ID necessary for non-NYU visitors)
THE COURANT LECTURES
Created to commemorate Richard Courant’s 70th birthday on January 8, 1958, the Courant Lectures officially began when friends established a fund to endow a series of lectures to be delivered every two years. The first speaker was Eugene Wigner in 1959, one of the greatest mathematical physicists of the 20th century and recipient of the 1963 Nobel Prize in Physics. His talk, “The Unreasonable Effectiveness of Mathematics in the Natural Sciences,” gained great notoriety and was subsequently published in Communications on Pure and Applied Mathematics.
In 2006, the lecture series was re-invigorated through generous endowment gifts from Dan Stroock (in memory of Alan M. Stroock, a longtime supporter of NYU) and the Gopal Varadhan Foundation (established in memory of Gopal Varadhan, alumnus of New York University and son of Courant Institute Professor of Mathematics and Abel Prize winner Raghu Varadhan; Gopal lost his life in the September 11, 2001 attacks on the World Trade Center).
BIO
Bernhard Schölkopf, a Director at the Max Planck Institute for Intelligent Systems in Tübingen, Germany, where he heads the Department of Empirical Inference, will be the speaker for this year’s Courant Lectures, presented by the Courant Institute of Mathematical Sciences.
Bernhard Schölkopf: Machine Learning and Kernel Methods
A leading researcher in the machine learning community, Bernhard Schölkopf is particularly active in the field of kernel methods. A large part of his work is the development of novel machine learning algorithms through their formulation as optimization problems.