2623 search results - page 338 / 525 » Universal Learning Theory |
191
click to vote
NN
2000
Springer
15 years 6 months ago
2000
Springer
Local minima and plateaus pose a serious problem in learning of neural networks. We investigate the hierarchical geometric structure of the parameter space of three-layer perceptr...
172
click to vote
IDA
2002
Springer
15 years 6 months ago
2002
Springer
Most classification methods are based on the assumption that the data conforms to a stationary distribution. However, the real-world data is usually collected over certain periods...
185
click to vote
COLT
2010
Springer
15 years 4 months ago
2010
Springer
We analyze the regret, measured in terms of log loss, of the maximum likelihood (ML) sequential prediction strategy. This "follow the leader" strategy also defines one o...
270
click to vote
CVPR
2012
IEEE
13 years 9 months ago
2012
IEEE
The launch of Xbox Kinect has built a very successful computer vision product and made a big impact to the gaming industry; this sheds lights onto a wide variety of potential appl...
157
click to vote
STOC
2003
ACM
16 years 6 months ago
2003
ACM
Boosting algorithms are procedures that "boost" low-accuracy weak learning algorithms to achieve arbitrarily high accuracy. Over the past decade boosting has been widely...