Learning With a Nontrivial Teacher — A lecture by Dr. Vladimir Vapnik
Wednesday, March 12, 2014 from 4:00 PM to 6:00 PM (EDT)
New York, NY
Please join us for "Learning With a Nontrivial Teacher — A lecture by Dr. Vladimir Vapnik", a free event for the scientific community — graduate level and higher — at the Simons Foundation, located on 21st Street in Manhattan. Limited seating is available on a first-come, first-served basis. We encourage you to obtain tickets online now through Eventbrite.
Learning Using Privileged Information (LUPI) is a new paradigm that uses an intelligent agent (a "nontrivial teacher") to supplement standard training data in the context of supervised learning algorithms. Rather than using standard, brute-force methods to address the general problem of inference and the construction of intelligent machines, the LUPI learning model allows the teacher to add additional (privileged) information to the training examples.
This can take the form of comments, descriptions, metaphoric reasoning and other teaching tactics. The goal is to develop good decision rules even when only a small number of examples is provided.
About the Speaker
Vladimir Vapnik, Ph.D., works in the machine learning department at NEC Laboratories America, Inc. and is professor of computer science at Columbia University. He has made major contributions to computer science and machine learning, including a general theory for minimizing the expected risk of losses using empirical data, and the widely used Support Vector Machine approach to classification. Among his many honors are the 2003 Humboldt Research Award, the 2005 Gabor Award, the 2010 Neural Networks Pioneer Award, the 2012 IEEE Frank Rosenblatt Award and the 2012 Benjamin Franklin Medal in Computer and Cognitive Science from the Franklin Institute. He was elected to the National Academy of Engineering in 2006 for "insights into the fundamental complexities of learning and for inventing practical and widely applied machine-learning algorithms."
The Frontiers of Data Science lecture series provides a venue to present and discuss new algorithms and techniques aimed at organizing and exploring the vast amounts of information that are becoming available in the natural and physical sciences.
Doors open 3:45PM
Lecture and Q&A 4:30-6:00PM
Gerald D. Fischbach Auditorium
160 Fifth Avenue, 2nd Floor
(Entrance on 21st Street)
New York, NY 10010
The Gerald D. Fischbach Auditorium offers accessible seating to patrons with special access needs. Please fill out the special accommodations request when ordering your ticket online.
Simons Foundation Lectures schedule is available here.
When & Where
Simons Foundation Lectures
The Simons Foundation launched the Simons Foundation Lectures in 2013 with the intention of drawing area scientists and scholars together around diverse and important topics in mathematics, physics, computer science, life sciences and autism research.
To read more about the Simons Foundation mission and its programs, please visit simonsfoundation.org.