Sciweavers

1096 search results - page 118 / 220
» A New Approach for Speeding Up Enumeration Algorithms
Sort
View
GECCO
2010
Springer
153views Optimization» more  GECCO 2010»
15 years 9 months ago
Multi-task evolutionary shaping without pre-specified representations
Shaping functions can be used in multi-task reinforcement learning (RL) to incorporate knowledge from previously experienced tasks to speed up learning on a new task. So far, rese...
Matthijs Snel, Shimon Whiteson
EMNLP
2011
14 years 6 months ago
Lateen EM: Unsupervised Training with Multiple Objectives, Applied to Dependency Grammar Induction
We present new training methods that aim to mitigate local optima and slow convergence in unsupervised training by using additional imperfect objectives. In its simplest form, lat...
Valentin I. Spitkovsky, Hiyan Alshawi, Daniel Jura...
RTSS
2006
IEEE
16 years 12 days ago
Tightening the Bounds on Feasible Preemption Points
Caches have become invaluable for higher-end architectures to hide, in part, the increasing gap between processor speed and memory access times. While the effect of caches on timi...
Harini Ramaprasad, Frank Mueller
APBC
2004
166views Bioinformatics» more  APBC 2004»
15 years 7 months ago
A Novel Method for Protein Subcellular Localization Based on Boosting and Probabilistic Neural Network.
Subcellular localization is a key functional characteristic of proteins. An automatic, reliable and efficient prediction system for protein subcellular localization is needed for ...
Jian Guo, Yuanlie Lin, Zhirong Sun
CEC
2009
IEEE
16 years 1 months ago
Tackling high dimensional nonseparable optimization problems by cooperatively coevolving particle swarms
— This paper attempts to address the question of scaling up Particle Swarm Optimization (PSO) algorithms to high dimensional optimization problems. We present a cooperative coevo...
Xiaodong Li, Xin Yao