1.1 --- a/MIT-media-projects.org	Tue Mar 05 18:55:21 2013 +0000
     1.2 +++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
     1.3 @@ -1,24 +0,0 @@
     1.4 -*Machine Learning and Pattern Recognition with Multiple
     1.5 -Modalities Hyungil Ahn and Rosalind W. Picard
     1.6 -
     1.7 -This project develops new theory and algorithms to enable
     1.8 -computers to make rapid and accurate inferences from
     1.9 -multiple modes of data, such as determining a person's
    1.10 -affective state from multiple sensors--video, mouse behavior,
    1.11 -chair pressure patterns, typed selections, or
    1.12 -physiology. Recent efforts focus on understanding the level
    1.13 -of a person's attention, useful for things such as
    1.14 -determining when to interrupt. Our approach is Bayesian:
    1.15 -formulating probabilistic models on the basis of domain
    1.16 -knowledge and training data, and then performing inference
    1.17 -according to the rules of probability theory. This type of
    1.18 -sensor fusion work is especially challenging due to problems
    1.19 -of sensor channel drop-out, different kinds of noise in
    1.20 -different channels, dependence between channels, scarce and
    1.21 -sometimes inaccurate labels, and patterns to detect that are
    1.22 -inherently time-varying. We have constructed a variety of
    1.23 -new algorithms for solving these problems and demonstrated
    1.24 -their performance gains over other state-of-the-art methods.
    1.25 -
    1.26 -http://affect.media.mit.edu/projectpages/multimodal/
    1.27 -