Sciweavers

2244 search results - page 376 / 449
» A new heuristic approach for non-convex optimization problem...
Sort
View
GECCO
2009
Springer
188views Optimization» more  GECCO 2009»
15 years 3 months ago
Exploiting multiple classifier types with active learning
Many approaches to active learning involve training one classifier by periodically choosing new data points about which the classifier has the least confidence, but designing a co...
Zhenyu Lu, Josh Bongard
ICWS
2007
IEEE
15 years 1 months ago
Improved Adaptation of Web Service Compositions Using Value of Changed Information
Workflows often operate in volatile environments in which the component services’ QoS changes frequently. Optimally adapting to these changes becomes an important problem that ...
Girish Chafle, Prashant Doshi, John Harney, Sumit ...
ECAI
2010
Springer
15 years 29 days ago
Unsupervised Layer-Wise Model Selection in Deep Neural Networks
Abstract. Deep Neural Networks (DNN) propose a new and efficient ML architecture based on the layer-wise building of several representation layers. A critical issue for DNNs remain...
Ludovic Arnold, Hélène Paugam-Moisy,...
IANDC
2008
122views more  IANDC 2008»
14 years 12 months ago
Automata can show PSpace results for description logics
In the area of Description Logic (DL), both tableau-based and automata-based algorithms are frequently used to show decidability and complexity results for basic inference problem...
Franz Baader, Jan Hladik, Rafael Peñaloza
MICAI
2010
Springer
14 years 10 months ago
Teaching a Robot to Perform Tasks with Voice Commands
The full deployment of service robots in daily activities will require the robot to adapt to the needs of non-expert users, particularly, to learn how to perform new tasks from “...
Ana C. Tenorio-Gonzalez, Eduardo F. Morales, Luis ...