Sciweavers

109 search results - page 21 / 22
» An Empirical Evaluation of Data-Driven Paraphrase Generation...
Sort
View
JMLR
2010
148views more  JMLR 2010»
14 years 4 months ago
A Generalized Path Integral Control Approach to Reinforcement Learning
With the goal to generate more scalable algorithms with higher efficiency and fewer open parameters, reinforcement learning (RL) has recently moved towards combining classical tec...
Evangelos Theodorou, Jonas Buchli, Stefan Schaal
CGO
2010
IEEE
15 years 4 months ago
Automatic creation of tile size selection models
Tiling is a widely used loop transformation for exposing/exploiting parallelism and data locality. Effective use of tiling requires selection and tuning of the tile sizes. This is...
Tomofumi Yuki, Lakshminarayanan Renganarayanan, Sa...
CIKM
2009
Springer
15 years 4 months ago
MKEM: a multi-level knowledge emergence model for mining undiscovered public knowledge
Background: Since Swanson proposed the Undiscovered Public Knowledge (UPK) model, there have been many approaches to uncover UPK by mining the biomedical literature. These earlier...
Ali Zeeshan Ijaz, Min Song, Doheon Lee
MICRO
2006
IEEE
127views Hardware» more  MICRO 2006»
15 years 3 months ago
A Predictive Performance Model for Superscalar Processors
Designing and optimizing high performance microprocessors is an increasingly difficult task due to the size and complexity of the processor design space, high cost of detailed si...
P. J. Joseph, Kapil Vaswani, Matthew J. Thazhuthav...
87
Voted
GECCO
2010
Springer
207views Optimization» more  GECCO 2010»
15 years 2 months ago
Generalized crowding for genetic algorithms
Crowding is a technique used in genetic algorithms to preserve diversity in the population and to prevent premature convergence to local optima. It consists of pairing each offsp...
Severino F. Galán, Ole J. Mengshoel