About
The Open House is part of the PASCAL's fifth thematic programme. This scientific programme brings together researchers around two themes:
- learning tasks where the target is complex (i.e. large number of different predictions) but has structure (sequence, tree, graph) that can be utilized for learning effectively;
- multi-task learning, where several dependent learning tasks are to be tackled at once.
In particular, we shall focus on the following research topics/issues.
Videos
Introductions

07:54
Introduction
Feb 25, 2007
·
5318 views
Lectures

56:25
Multitask learning: the Bayesian way
Feb 25, 2007
·
6017 views

24:56
How to Teach Support Vector Machine to Learn Vector Outputs
Feb 25, 2007
·
6522 views

20:40
XML structure mapping
Feb 25, 2007
·
5809 views

48:05
Estimation of gradients and coordinate covariation in classification
Feb 25, 2007
·
4414 views

01:04:00
Inductive transfer via embeddings into a common feature space
Feb 25, 2007
·
3359 views

01:03:55
Going beyond bag-of-words: dealing with a text as a graph of triples
Feb 25, 2007
·
8728 views

55:51
Output kernel tree
Feb 25, 2007
·
4559 views

50:24
Multi-task feature learning
Feb 25, 2007
·
7171 views

13:48
Learning Structured Outputs via Kernel Dependency Estimation and Stochastic Gram...
Feb 25, 2007
·
3444 views

29:59
Targeted PDF Learning
Feb 25, 2007
·
4862 views

31:47
Machine Learning for Sequential Data: A Comparative Study with Applications to N...
Feb 25, 2007
·
6917 views

36:15
Slow subspace learning from stationary processes
Feb 25, 2007
·
3128 views

01:20:01
Learning shared representations for object recognition
Feb 25, 2007
·
9666 views

47:57
Efficient max-margin Markov learning via conditional gradient and probabilistic ...
Feb 25, 2007
·
4328 views

50:05
Learning Nonparametric Priors from Multiple Tasks
Feb 25, 2007
·
4392 views

01:08:00
Top-down vs. bottom-up methods for hierarchical classification
Feb 25, 2007
·
8346 views

19:38
Learning with structured inputs
Feb 25, 2007
·
3384 views