Sciweavers

12943 search results - page 168 / 2589
» Predicting When Not to Predict
Sort
View
IJCAI
2003
13 years 11 months ago
On the Foundations of Expected Expected Utility
Intelligent agents often need to assess user utility functions in order to make decisions on their behalf, or predict their behavior. When uncertainty exists over the precise natu...
Craig Boutilier
WSC
2004
13 years 11 months ago
Simulation Input Updating Using Bayesian Techniques
Simulation built on assumption and approximation has been traditionally utilized to make predictions prior to construction. Although there are many benefits of simulation such as ...
Tae Hwan Chung, Yasser Mohamed, Simaan M. AbouRizk
ICANN
2010
Springer
13 years 11 months ago
Using Reinforcement Learning to Guide the Development of Self-organised Feature Maps for Visual Orienting
We present a biologically inspired neural network model of visual orienting (using saccadic eye movements) in which targets are preferentially selected according to their reward va...
Kevin Brohan, Kevin N. Gurney, Piotr Dudek
GLVLSI
2007
IEEE
173views VLSI» more  GLVLSI 2007»
13 years 10 months ago
Modeling and estimating leakage current in series-parallel CMOS networks
This paper reviews the modeling of subthreshold leakage current and proposes an improved model for general series-parallel CMOS networks. The presence of on-switches in off-networ...
Paulo F. Butzen, André Inácio Reis, ...
CSDA
2007
148views more  CSDA 2007»
13 years 10 months ago
Classifying densities using functional regression trees: Applications in oceanology
The problem of building a regression tree is considered when the response variable is a probability density function. Splitting criteria which are well adapted to measure the diss...
David Nerini, Badih Ghattas