Sciweavers

1227 search results - page 189 / 246
» Learning Rates for Q-Learning
Sort
View
JMLR
2008
230views more  JMLR 2008»
13 years 10 months ago
Exponentiated Gradient Algorithms for Conditional Random Fields and Max-Margin Markov Networks
Log-linear and maximum-margin models are two commonly-used methods in supervised machine learning, and are frequently used in structured prediction problems. Efficient learning of...
Michael Collins, Amir Globerson, Terry Koo, Xavier...
ICCV
2009
IEEE
15 years 2 months ago
What is the Best Multi-Stage Architecture for Object Recognition?
In many recent object recognition systems, feature extraction stages are generally composed of a filter bank, a non-linear transformation, and some sort of feature pooling layer...
Kevin Jarrett, Koray Kavukcuoglu, Marc’Aurelio R...
ICCV
2007
IEEE
14 years 12 months ago
A Scalable Approach to Activity Recognition based on Object Use
We propose an approach to activity recognition based on detecting and analyzing the sequence of objects that are being manipulated by the user. In domains such as cooking, where m...
Jianxin Wu, Adebola Osuntogun, Tanzeem Choudhury, ...
KDD
2006
ACM
155views Data Mining» more  KDD 2006»
14 years 10 months ago
Camouflaged fraud detection in domains with complex relationships
We describe a data mining system to detect frauds that are camouflaged to look like normal activities in domains with high number of known relationships. Examples include accounti...
Sankar Virdhagriswaran, Gordon Dakin
SECON
2008
IEEE
14 years 4 months ago
Optimal Buffer Management Policies for Delay Tolerant Networks
—Delay Tolerant Networks are wireless networks where disconnections may occur frequently due to propagation phenomena, node mobility, and power outages. Propagation delays may al...
Amir Krifa, Chadi Barakat, Thrasyvoulos Spyropoulo...