Sciweavers

1351 search results - page 12 / 271
» Learning from compressed observations
Sort
View
ICRA
2010
IEEE
147views Robotics» more  ICRA 2010»
13 years 5 months ago
Learning physically-instantiated game play through visual observation
Abstract— We present an integrated vision and robotic system that plays, and learns to play, simple physically-instantiated board games that are variants of TIC TAC TOE and HEXAP...
Andrei Barbu, Siddharth Narayanaswamy, Jeffrey Mar...
COLT
2008
Springer
13 years 9 months ago
Learning from Collective Behavior
Inspired by longstanding lines of research in sociology and related fields, and by more recent largepopulation human subject experiments on the Internet and the Web, we initiate a...
Michael Kearns, Jennifer Wortman
ICASSP
2010
IEEE
13 years 6 months ago
Human detection in images via L1-norm Minimization Learning
In recent years, sparse representation originating from signal compressed sensing theory has attracted increasing interest in computer vision research community. However, to our b...
Ran Xu, Baochang Zhang, Qixiang Ye, Jianbin Jiao
KI
2008
Springer
13 years 7 months ago
Learning by Observing: Case-Based Decision Making in Complex Strategy Games
Abstract. There is a growing research interest in the design of competitive and adaptive Game AI for complex computer strategy games. In this paper, we present a novel approach for...
Darko Obradovic, Armin Stahl
ICML
2010
IEEE
13 years 8 months ago
Efficient Learning with Partially Observed Attributes
We describe and analyze efficient algorithms for learning a linear predictor from examples when the learner can only view a few attributes of each training example. This is the ca...
Nicolò Cesa-Bianchi, Shai Shalev-Shwartz, O...