Sciweavers

11321 search results - page 177 / 2265
» Improvements to Turing's method
Sort
View
ECML
2007
Springer
16 years 23 days ago
Nondeterministic Discretization of Weights Improves Accuracy of Neural Networks
Abstract. The paper investigates modification of backpropagation algorithm, consisting of discretization of neural network weights after each training cycle. This modification, a...
Marcin Wojnarski
ICAS
2005
IEEE
95views Robotics» more  ICAS 2005»
16 years 6 days ago
Improving APS with Anchor Selection in Anisotropic Sensor Networks
Sensor networks are useful for environmental monitoring, military applications, disaster management, etc. In many applications, sensors are supposed to know their geographic locat...
King-Yip Cheng, Vincent Tam, King-Shan Lui
ICRA
2005
IEEE
131views Robotics» more  ICRA 2005»
16 years 5 days ago
Model-based Shape Analysis of Gas Concentration Gridmaps for Improved Gas Source Localisation
Abstract— This work addresses the capability to use concentration gridmaps to locate a static gas source. In previous works it was found that depending on the shape of the mapped...
Achim J. Lilienthal, Felix Streichert, Andreas Zel...
GECCO
2005
Springer
119views Optimization» more  GECCO 2005»
16 years 3 days ago
Improving GA search reliability using maximal hyper-rectangle analysis
In Genetic algorithms it is not easy to evaluate the confidence level in whether a GA run may have missed a complete area of good points, and whether the global optimum was found....
Chongshan Zhang, Khaled Rasheed
NOLISP
2005
Springer
16 years 2 days ago
Weighting Scores to Improve Speaker-Dependent Threshold Estimation in Text-Dependent Speaker Verification
The difficulty of obtaining data from impostors and the scarcity of data are two factors that have a large influence in the estimation of speakerdependent thresholds in text-depend...
Javier R. Saeta, Javier Hernando