[Ml-stat-talks] Vapnik talk, mon, 11/29, 3pm, CS sm. aud.

Matt Hoffman mdhoffma at CS.Princeton.EDU
Mon Nov 22 18:19:04 EST 2010

I saw this talk at NYU a week or two ago (where it probably set some
attendance records), and highly recommend checking it out. A good mix
of intuition and theory, plus a chance to get some insight into how a
giant of the field thinks.


On Mon, Nov 22, 2010 at 9:35 PM, Robert Schapire
<schapire at cs.princeton.edu> wrote:
> Vladimir Vapnik, who is renowned for his pioneering and extremely
> high-impact work on machine learning, will give a talk this coming Monday,
> November 29, at 3pm in the small auditorium (room 105) of the Computer
> Science building.  See the abstract below.
>                      Vladimir Vapnik
> Abstract.
> The existing machine learning paradigm considers a simple scheme:
> given a set of training examples find in a given collection of
> functions the one that in the best possible way approximates the
> unknown decision rule. In such a paradigm a teacher does not play any
> role.
> In human learning, however, the role of a teacher is very important:
> along with examples a teacher provides students with explanations,
> comments, comparisons, and so on. In this talk I will introduce
> elements of human teaching in machine learning.  I will introduce an
> advanced learning paradigm called learning using privileged
> information (LUPI), where at the training stage a teacher gives some
> additional information about training examples. This privileged
> information will not be available during test stage.
> I will consider LUPI paradigm for support vector machine type of
> algorithms and demonstrate big superiority of the advanced learning
> paradigm over classical one.
> The new learning paradigm is general; it can be apply to almost any
> learning problem.

More information about the Ml-stat-talks mailing list