Sciweavers

232 search results - page 16 / 47
» Learning all optimal policies with multiple criteria
Sort
View
FLAIRS
2004
13 years 10 months ago
Developing Task Specific Sensing Strategies Using Reinforcement Learning
Robots that can adapt and perform multiple tasks promise to be a powerful tool with many applications. In order to achieve such robots, control systems have to be constructed that...
Srividhya Rajendran, Manfred Huber
CVPR
2009
IEEE
15 years 3 months ago
A Min-Max Framework of Cascaded Classifier with Multiple Instance Learning for Computer Aided Diagnosis
The computer aided diagnosis (CAD) problems of detecting potentially diseased structures from medical images are typically distinguished by the following challenging characterist...
Dijia Wu (Rensselaer Polytechnic Institute), Jinbo...
GECCO
2006
Springer
159views Optimization» more  GECCO 2006»
14 years 4 days ago
Smart crossover operator with multiple parents for a Pittsburgh learning classifier system
This paper proposes a new smart crossover operator for a Pittsburgh Learning Classifier System. This operator, unlike other recent LCS approaches of smart recombination, does not ...
Jaume Bacardit, Natalio Krasnogor
AAAI
2010
13 years 10 months ago
Multi-Task Active Learning with Output Constraints
Many problems in information extraction, text mining, natural language processing and other fields exhibit the same property: multiple prediction tasks are related in the sense th...
Yi Zhang 0010
IEEEPACT
2006
IEEE
14 years 2 months ago
Communist, utilitarian, and capitalist cache policies on CMPs: caches as a shared resource
As chip multiprocessors (CMPs) become increasingly mainstream, architects have likewise become more interested in how best to share a cache hierarchy among multiple simultaneous t...
Lisa R. Hsu, Steven K. Reinhardt, Ravishankar R. I...