Sciweavers

3084 search results - page 68 / 617
» Learning to Take Actions
Sort
View
ECCV
2008
Springer
15 years 11 months ago
Latent Pose Estimator for Continuous Action Recognition
Recently, models based on conditional random fields (CRF) have produced promising results on labeling sequential data in several scientific fields. However, in the vision task of c...
Huazhong Ning, Wei Xu, Yihong Gong, Thomas S. Huan...
SIGECOM
2006
ACM
139views ECommerce» more  SIGECOM 2006»
15 years 3 months ago
Playing games in many possible worlds
In traditional game theory, players are typically endowed with exogenously given knowledge of the structure of the game—either full omniscient knowledge or partial but fixed in...
Matt Lepinski, David Liben-Nowell, Seth Gilbert, A...
ICRA
1995
IEEE
123views Robotics» more  ICRA 1995»
15 years 1 months ago
Vision-Based Reinforcement Learning for Purposive Behavior Acquisition
This paper presents a method of vision-based reinforcement learning by which a robot learns to shoot a ball into a goal, and discusses several issues in applying the reinforcement...
Minoru Asada, Shoichi Noda, Sukoya Tawaratsumida, ...
ALT
2011
Springer
13 years 9 months ago
On the Expressive Power of Deep Architectures
Deep architectures are families of functions corresponding to deep circuits. Deep Learning algorithms are based on parametrizing such circuits and tuning their parameters so as to ...
Yoshua Bengio, Olivier Delalleau
ICTCS
2007
Springer
15 years 4 months ago
Weak Markovian Bisimilarity: Abstracting from Prioritized/Weighted Internal Immediate Actions
ing from Prioritized/Weighted Internal Immediate Actions Marco Bernardo and Alessandro Aldini Universit`a di Urbino “Carlo Bo” – Italy Markovian process calculi constitute a ...
Marco Bernardo, Alessandro Aldini