590 search results - page 40 / 118 » Can We Learn to Beat the Best Stock |
ICML
2010
IEEE
14 years 10 months ago
2010
IEEE
We develop a semi-supervised learning method that constrains the posterior distribution of latent variables under a generative model to satisfy a rich set of feature expectation c...
WAIM
2004
Springer
15 years 3 months ago
2004
Springer
A top-N selection query against a relation is to find the N tuples that satisfy the query condition the best but not necessarily completely. In this paper, we propose a new method ...
ICML
2002
IEEE
15 years 10 months ago
2002
IEEE
ROC analysis is increasingly being recognised as an important tool for evaluation and comparison of classifiers when the operating characteristics (i.e. class distribution and cos...
GECCO
2005
Springer
15 years 3 months ago
2005
Springer
Recurrent neural networks are theoretically capable of learning complex temporal sequences, but training them through gradient-descent is too slow and unstable for practical use i...
CVPR
2010
IEEE
15 years 6 months ago
2010
IEEE
Many successful models for scene or object recognition transform low-level descriptors (such as Gabor filter responses, or SIFT descriptors) into richer representations of interme...