Sciweavers

46 search results - page 7 / 10
» Noise-injected neural networks show promise for use on small...
Sort
View
JMLR
2012
11 years 11 months ago
Random Search for Hyper-Parameter Optimization
Grid search and manual search are the most widely used strategies for hyper-parameter optimization. This paper shows empirically and theoretically that randomly chosen trials are ...
James Bergstra, Yoshua Bengio
IJCNN
2006
IEEE
14 years 2 months ago
A Variational EM Approach to Predicting Uncertainty in Supervised Learning
— In many applications of supervised learning, the conditional average of the target variables is not sufficient for prediction. The dependencies between the explanatory variabl...
Markus Harva
BIOWIRE
2007
Springer
14 years 16 days ago
An Artificial Chemistry for Networking
Chemical computing models have been proposed since the 1980ies for expressing concurrent computations in elegant ways for shared memory systems. In this paper we look at the distri...
Thomas Meyer, Lidia Yamamoto, Christian F. Tschudi...
NN
2006
Springer
163views Neural Networks» more  NN 2006»
13 years 8 months ago
Machine learning approaches for estimation of prediction interval for the model output
A novel method for estimating prediction uncertainty using machine learning techniques is presented. Uncertainty is expressed in the form of the two quantiles (constituting the pr...
Durga L. Shrestha, Dimitri P. Solomatine
ICUMT
2009
13 years 6 months ago
Performance of relay-enabled uplink in cellular networks - a flow level analysis
Uplink users in cellular networks, such as UMTS/ HSPA, located at the edge of the cell generally suffer from poor channel conditions. Deploying intermediate relay nodes is seen as ...
Desislava C. Dimitrova, Hans van den Berg, Geert J...