995 search results - page 131 / 199 » Learning Useful Horn Approximations |
114
Voted
ECCV
2004
Springer
16 years 2 months ago
2004
Springer
We consider object recognition as the process of attaching meaningful labels to specific regions of an image, and propose a model that learns spatial relationships between objects....
152
Voted
JMLR
2010
14 years 7 months ago
2010
With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...
100
Voted
ILP
2007
Springer
15 years 7 months ago
2007
Springer
Bias/variance analysis is a useful tool for investigating the performance of machine learning algorithms. Conventional analysis decomposes loss into errors due to aspects of the le...
107
click to vote
ICML
1994
IEEE
15 years 4 months ago
1994
IEEE
Compositional Q-Learning (CQ-L) (Singh 1992) is a modular approach to learning to performcomposite tasks made up of several elemental tasks by reinforcement learning. Skills acqui...
114
Voted
ICML
2010
IEEE
15 years 1 months ago
2010
IEEE
We propose a novel boosting algorithm which improves on current algorithms for weighted voting classification by striking a better balance between classification accuracy and the ...