"Learning Richly Structured Representations from Weakly Annotated Data" (This Year at the DeGroot Lecture)
Attention conservation notice: Only of interest if you (1)
care about learning complex stochastic models from limited data, and (2) are in
The CMU statistics department sponsors an annual distinguished lecture
series in memory of our sainted
H. DeGroot. This year, it comes at the end of the workshop on
Case Studies in Bayesian Statistics and
Machine Learning. We are very happy to have as the lecturer
- "Learning Richly Structured Representations from Weakly Annotated Data"
- Abstract: The solution to many complex problems require that we
build up a representation that spans multiple levels of abstraction. For
example, to obtain a semantic scene understanding from an image, we need to
detect and identify objects and assign pixels to objects, understand scene
geometry, derive object pose, and reconstruct the relationships between
- Fully annotated data for learning richly structured models can be obtained
in very limited quantities; hence, for such applications and many others, we
need to learn models from data where many of the relevant variables are
unobserved. I will describe novel machine learning methods that can train
models using weakly labeled data, thereby making use of much larger amounts of
available data, with diverse levels of annotation. These models are inspired
by ideas from human learning, in which the complexity of the learned models and
the difficulty of the training instances tackled changes over the course of the
learning process. We will demonstrate the applicability of these ideas of
various problems, focusing on the problem of holistic computer vision.
- Time and place:: 4:15 pm on Friday, 14 October 2011, in the
McConomy Auditorium in the University Center
As always, the talk is free and open to the public.
Update, after the talk: We more than filled the auditorium; I had
to sit on the stairs.
Enigmas of Chance
Posted at October 07, 2011 18:00 | permanent link