Sciweavers

2075 search results - page 110 / 415
» Learning better transliterations
Sort
View
IDA
2010
Springer
15 years 3 months ago
Multi-dimensional data construction method with its application to learning from small-sample-sets
Insufficient training data is one of the major problems in neural network learning, because it leads to poor learning performance. In order to enhance an intelligent learning proc...
Hsiao-Fan Wang, Chun-Jung Huang
ICASSP
2009
IEEE
15 years 2 months ago
Target detection using incremental learning on single-trial evoked response
The human neural responses associated with cognitive events, referred as event related potentials (ERPs), can provide reliable inference for target image detection. Incremental le...
Yonghong Huang, Deniz Erdogmus, Misha Pavel, Kenne...
JMLR
2010
106views more  JMLR 2010»
14 years 11 months ago
Why Does Unsupervised Pre-training Help Deep Learning?
Much recent research has been devoted to learning algorithms for deep architectures such as Deep Belief Networks and stacks of auto-encoder variants, with impressive results obtai...
Dumitru Erhan, Yoshua Bengio, Aaron C. Courville, ...
ICML
2007
IEEE
16 years 5 months ago
On the role of tracking in stationary environments
It is often thought that learning algorithms that track the best solution, as opposed to converging to it, are important only on nonstationary problems. We present three results s...
Richard S. Sutton, Anna Koop, David Silver
ICML
2005
IEEE
16 years 5 months ago
Linear Asymmetric Classifier for cascade detectors
The detection of faces in images is fundamentally a rare event detection problem. Cascade classifiers provide an efficient computational solution, by leveraging the asymmetry in t...
Jianxin Wu, Matthew D. Mullin, James M. Rehg