Sciweavers

472 search results - page 24 / 95
» Linear programming with online learning
Sort
View
JMLR
2002
135views more  JMLR 2002»
13 years 7 months ago
Covering Number Bounds of Certain Regularized Linear Function Classes
Recently, sample complexity bounds have been derived for problems involving linear functions such as neural networks and support vector machines. In many of these theoretical stud...
Tong Zhang
GECCO
2010
Springer
191views Optimization» more  GECCO 2010»
13 years 7 months ago
Fitness importance for online evolution
To complement standard fitness functions, we propose "Fitness Importance" (FI) as a novel meta-heuristic for online learning systems. We define FI and show how it can be...
Philip Valencia, Raja Jurdak, Peter Lindsay
ICML
2006
IEEE
14 years 1 months ago
Automatic basis function construction for approximate dynamic programming and reinforcement learning
We address the problem of automatically constructing basis functions for linear approximation of the value function of a Markov Decision Process (MDP). Our work builds on results ...
Philipp W. Keller, Shie Mannor, Doina Precup
ICML
2006
IEEE
14 years 8 months ago
Kernel Predictive Linear Gaussian models for nonlinear stochastic dynamical systems
The recent Predictive Linear Gaussian model (or PLG) improves upon traditional linear dynamical system models by using a predictive representation of state, which makes consistent...
David Wingate, Satinder P. Singh
ICALT
2008
IEEE
14 years 2 months ago
Cultivating a Landscape of Online Places for a Developmental Learning Community
We describe our work on seeding and building a developmental learning community for recruiting and retaining women in educational programs and careers related to computing and inf...
Mary Beth Rosson, Hansa Sinha, Dejin Zhao, John M....