- 10:00 Introduction, Yann LeCun (Courant)
- 10:10 Ralph Grishman (Courant/Computer Science)
- "Learning Methods for Information Extraction from Text"
Home Page
- 10:30 Satoshi Sekine (Courant/Computer Science)
- "Learning Methods in On-Demand Information Extraction"
Home Page
- 10:40 Dan Melamed (Courant/Computer Science)
- "Some Open Learning Problems in Computational Linguistics"
Home Page
- 10:50 Cynthia Rudin, Ingrid Daubechie (Courant/Math), Rob Schapire (Princeton)
- "The Dynamics of Boosting"
-
- 11:00-11:30 break
-
- 11:30 Foster Provost (Stern)
- "Machine Learning for Suspicion Scoring: from Fraud Detection to
Counterterrorism?"
Abstract;
Home Page
- 11:50: Denis Pelli (Psychology)
- "How People Learn a New Alphabet".
Home Page
- 12:10 Yann LeCun (Courant/Computer Science)
- "Learning to Recognize Object Categories"
Home Page
-
- 12:30-1:20 Lunch
-
- 1:20 Eero Simoncelli (CNS)
- "learning optimal image decomopositions and neural response models"
Home Page
- 1:40 Hannah Bayer, Paul Glimcher (CNS)
- "Midbrain dopamine neurons encode a quantitative reward prediction error signal"
- 2:00 Claudia Perlich (Stern)
- "Modeling in Complex Multi-Relational Domains"
- 2:10 Bill Greene (Stern)
- "Simulation-based Estimation Methods in Econometrics".
Home Page
- 2:40 Cliff Hurvich (Stern)
- "Forecasting volatility of high frequency returns on the S&P 500"
Home Page
-
- 3:00-3:30 Break
-
- 3:30 Souheil Inati, David Heeger (CNS)
- "Advanced MRI Applications for Neuroscience"
- 3:50 Alex Vasilescu, Demetri Terzopoulos (Courant/Computer Science)
- "TensorFaces"
Home Page
- 4:10 Panos Mavromatis (Steinhardt/Music)
- "Hidden Markov Models of Melodic Improvisation"
- 4:30 Wendy Suzuki (CNS)
- "Associative learning signals in the medial temporal lobe"
- 4:50 Vasant Dhar (Stern)
- "Genetic Search: Are simpler patterns more robust?"
Home Page
- 5:00 Sofus Macskassy (Stern)
- "The Relational Neighbor Classifier: Homophily in Action"
Abstract;
Home Page
- 5:10 Margaret Wright (Courant/CS)
- Optimization and Learning, Concluding Remarks.
-
- 5:20-5:40 Open Discussion
-
-
- 5:40 Adjourn
-
Everyone is welcome to attend, even if you have not registered,
but seating is limited to about 60 persons.
Lunch will be served at 12:30 for registered participants in the
room next to WWH-1302 where the talks take place.
An laptop projector and an overhead projector will be available for speakers.
NYU Learning Mailing List |
A mailing list for the NYU Learning community will be set up
shortly. If you want to be on the inital list, please send email
to yann AT cs.nyu.edu with the
following information (please include [NYUWCBL] in the subject line):
--------------------------------------------------- cut here ----
* Name:
* Email Address:
* Website:
* Department:
--------------------------------------------------- cut here ----
for information only, the deadline is passed
please disseminate this announcement within your group/lab/department/school
Dear Colleague,
We are glad to invite you to the first NYU Workshop on Computational
and Biological Learning. The purpose of this workshop is to bring
together people of the NYU community who are interested in learning,
whether their primary interest is to apply learning techniques in
their research, or whether their primary interest is to develop new
theories, techniques, and tools for machine learning, computational
models of biological learning, statistical estimation, and related
fields were computational models are derived from data.
Learning and Statistical Estimation methods are used in a wide variety
of domains spanning many academic disciplines at NYU: Computer
Science, Neuroscience, Psychology, Statistics, Mathematics,
Linguistics, Biology, Bioinformatics, Finance, Medicine, even Physics,
Music Theory, and the Performing Arts. Current applications of
learning methods include data mining, computer vision, natural
language processing, behavior modeling, biological modeling, financial
time-series prediction, weather prediction, DNA micro-array analysis,
gene finding and biological sequence analysis, brain imaging, modeling
improvised melodies, and many other topics.
Learning researchers are in search of interesting datasets to drive
the development of new learning algorithms, while users of learning
are in search of solutions to their data analysis and modeling
problems. Therefore this workshop's primary goal will be to provide a
forum in which researchers can exchange ideas and tips, advertise and
exchange software tools, find help on specific topics, find
interesting datasets to work with, and hopefully start new
collaborations.
The workshop will be an informal get-together with short presentations
(10 minutes), regular talks (20 minutes), and a small number of
tutorial talks (30 minutes). A poster session (mostly for student
projects) will also be held.
Talks may belong to the following (non-exhaustive) list of categories:
- A - descriptions of problems in various application areas that could
profit from new advances in learning, or from collaborations
between domain specialists and learning researchers.
- B - descriptions of successful uses of learning techniques in
past or on-going research projects.
- C - descriptions of new ideas, learning algorithms, or software tools
that can be used by the NYU Learning community.
- D - presentation of research projects and results in biological
or computational learning.
Application domains: Neuroscience, Psychology/Linguistics,
Biology/Bio-informatics/Chemistry, Numerical Modeling/Physics,
Computer Science/Artificial Intelligence, Finance/Economy,
Statistics/Operations Research, Arts, Others.
- Yann LeCun (Courant) [ yann AT cs.nyu.edu ]
- Foster Provost (Stern) [ fprovost AT stern.nyu.edu ]
- Eero Simoncelli (CNS) [ eero AT cns.nyu.edu ]
- Demetri Terzopoulos (Courant) [ dt AT cs.nyu.edu ]