Home
Overview
Call for
participation
Important Dates
Participants
Schedule
Accepted Papers
Resources
Sponsors
|
|
|
|
Home
Inductive
Transfer: 10 Years Later will be held as a post conference workshop
following NIPS 2005, on Friday, December 9, at the
Westin Resort and Spa in Whistler,
British Columbia, Canada.
Inductive transfer or transfer
learning refers to the problem of retaining and applying the
knowledge learned in one or more tasks
to efficiently develop an effective hypothesis for a new task.
While all learning
involves generalization across problem instances, transfer learning
emphasizes the transfer of knowledge across domains, tasks, and
distributions that are similar but not the same. For example,
learning to recognize chairs might help to recognize tables; or
learning to play checkers might improve the learning of chess. At
NIPS95 a two-day workshop on "Learning to Learn" that focused on the
need for lifelong machine learning methods that retain and reuse
learned knowledge. This NIPS 2005 workshop will examine
the progress that has been made in ten years, the questions and
challenges that remain, and the opportunities for new applications
of inductive transfer systems.
Please see the
call for participation for more information on how to submit
workshop papers.
Current highlights
of the workshop are:
Invited speakers:
Rich Caruana -
Foundations / Survey of accepted theory
Shai Ben-David - New directions/Open questions, ML
Theory Perspective
Theodoros Evgeniou - New directions/Open questions,
Bayesian/Kernel Perspective
Tom Dietterich - Transfer Learning in the CALO
Project (Cognitive Assistant that Learns and
Organizes)
Panel/Discussion:
Morning: Progress? Why does learning
with zero prior knowledge continue to dominate
research?
Afternoon: What are the three most important problems to work
on in future research?
A related workshop "Interclass
Transfer: why learning to recognize many objects is easier than
learning to recognize just one" will take place the following day,
Saturday, December 10. We are coordinating with the
organizers of this other workshop so that they will provide
complementary perspectives on these closely related topics.
This is great opportunity to learn more about an important and
growing area of Machine Learning.
|
| |