1227 search results - page 147 / 246 » Learning Rates for Q-Learning |
141
Voted
ICDAR
2007
IEEE
15 years 9 months ago
2007
IEEE
The Machine Learning and Pattern Recognition communities are facing two challenges: solving the normalization problem, and solving the deep learning problem. The normalization pro...
125
click to vote
TCSV
2008
15 years 3 months ago
2008
Conventional subspace learning or recent feature extraction methods consider globality as the key criterion to design discriminative algorithms for image classification. We demonst...
133
Voted
ECIR
2010
Springer
15 years 4 months ago
2010
Springer
Collaborative filtering is one of the most effective techniques for making personalized content recommendation. In the literature, a common experimental setup in the modeling phase...
170
Voted
ECCV
2004
Springer
16 years 5 months ago
2004
Springer
The problem of interactive foreground/background segmentation in still images is of great practical importance in image editing. The state of the art in interactive segmentation is...
149
Voted
NIPS
2004
15 years 4 months ago
2004
We use unsupervised probabilistic machine learning ideas to try to explain the kinds of learning observed in real neurons, the goal being to connect abstract principles of self-or...