83 search results - page 6 / 17 » Neural Network Learning: Testing Bounds on Sample Complexity |
ICML
2008
IEEE
14 years 8 months ago
2008
IEEE
Deep Belief Networks (DBN's) are generative models that contain many layers of hidden variables. Efficient greedy algorithms for learning and approximate inference have allow...
ICANN
2011
Springer
12 years 11 months ago
2011
Springer
Attribute importance measures for supervised learning are important for improving both learning accuracy and interpretability. However, it is well-known there could be bias when th...
EWRL
2008
13 years 9 months ago
2008
We consider reinforcement learning in the parameterized setup, where the model is known to belong to a parameterized family of Markov Decision Processes (MDPs). We further impose ...
BMCBI
2007
13 years 7 months ago
2007
Background: The four heterogeneous childhood cancers, neuroblastoma, non-Hodgkin lymphoma, rhabdomyosarcoma, and Ewing sarcoma present a similar histology of small round blue cell...
ICML
2007
IEEE
14 years 8 months ago
2007
IEEE
In supervised learning, we commonly assume that training and test data are sampled from the same distribution. However, this assumption can be violated in practice and then standa...