Sciweavers

380 search results - page 51 / 76
» Learning Recursive Control Programs from Problem Solving
Sort
View
ATAL
2005
Springer
14 years 28 days ago
Improving reinforcement learning function approximators via neuroevolution
Reinforcement learning problems are commonly tackled with temporal difference methods, which use dynamic programming and statistical sampling to estimate the long-term value of ta...
Shimon Whiteson
CCS
2004
ACM
14 years 24 days ago
Lessons learned using alloy to formally specify MLS-PCA trusted security architecture
In order to solve future Multi Level Security (MLS) problems, we have developed a solution based on the DARPA Polymorphous Computing Architecture (PCA). MLS-PCA uses a novel distr...
Brant Hashii
GECCO
2008
Springer
132views Optimization» more  GECCO 2008»
13 years 8 months ago
Hybridizing an evolutionary algorithm with mathematical programming techniques for multi-objective optimization
In recent years, the development of multi-objective evolutionary algorithms (MOEAs) hybridized with mathematical programming techniques has significantly increased. However, most...
Saúl Zapotecas Martínez, Carlos A. C...
BMCBI
2007
135views more  BMCBI 2007»
13 years 7 months ago
Detecting multivariate differentially expressed genes
Background: Gene expression is governed by complex networks, and differences in expression patterns between distinct biological conditions may therefore be complex and multivariat...
Roland Nilsson, José M. Peña, Johan ...
PLDI
2010
ACM
14 years 14 days ago
Smooth interpretation
We present smooth interpretation, a method to systematically approximate numerical imperative programs by smooth mathematical functions. This approximation facilitates the use of ...
Swarat Chaudhuri, Armando Solar-Lezama