Sciweavers

92 search results - page 2 / 19
» Jointly Learning to Extract and Compress
Sort
View
CORR
2007
Springer
112views Education» more  CORR 2007»
13 years 4 months ago
Learning from compressed observations
— The problem of statistical learning is to construct a predictor of a random variable Y as a function of a related random variable X on the basis of an i.i.d. training sample fr...
Maxim Raginsky
ICRA
2005
IEEE
138views Robotics» more  ICRA 2005»
13 years 10 months ago
The Role of Motion Information in Learning Human-Robot Joint Attention
— To realize natural human-robot interactions and investigate the developmental mechanism of human communication, an effective approach is to construct models by which a robot im...
Yukie Nagai
CIKM
2011
Springer
12 years 4 months ago
Semi-supervised multi-task learning of structured prediction models for web information extraction
Extracting information from web pages is an important problem; it has several applications such as providing improved search results and construction of databases to serve user qu...
Paramveer S. Dhillon, Sundararajan Sellamanickam, ...
ICASSP
2011
IEEE
12 years 8 months ago
Dynamics of tongue gestures extracted automatically from ultrasound
We describe a system for automatically extracting dynamics of tongue gestures from ultrasound images of the tongue using translational deep belief networks (tDBNs). In tDBNs, a jo...
Jeff Berry, Ian Fasel
FOCS
2009
IEEE
13 years 11 months ago
Extracting Correlations
Abstract— Motivated by applications in cryptography, we consider a generalization of randomness extraction and the related notion of privacy amplification to the case of two cor...
Yuval Ishai, Eyal Kushilevitz, Rafail Ostrovsky, A...