Sciweavers

567 search results - page 25 / 114
» Learning All Subfunctions of a Function
Sort
View
ICML
1999
IEEE
15 years 10 months ago
Least-Squares Temporal Difference Learning
Excerpted from: Boyan, Justin. Learning Evaluation Functions for Global Optimization. Ph.D. thesis, Carnegie Mellon University, August 1998. (Available as Technical Report CMU-CS-...
Justin A. Boyan
CDC
2010
IEEE
196views Control Systems» more  CDC 2010»
14 years 4 months ago
Convergence and convergence rate of stochastic gradient search in the case of multiple and non-isolated extrema
The asymptotic behavior of stochastic gradient algorithms is studied. Relying on some results of differential geometry (Lojasiewicz gradient inequality), the almost sure pointconve...
Vladislav B. Tadic
74
Voted
ICML
2003
IEEE
15 years 10 months ago
Learning with Positive and Unlabeled Examples Using Weighted Logistic Regression
The problem of learning with positive and unlabeled examples arises frequently in retrieval applications. We transform the problem into a problem of learning with noise by labelin...
Wee Sun Lee, Bing Liu
NN
2008
Springer
153views Neural Networks» more  NN 2008»
14 years 9 months ago
A biologically motivated visual memory architecture for online learning of objects
We present a biologically motivated architecture for object recognition that is based on a hierarchical feature-detection model in combination with a memory architecture that impl...
Stephan Kirstein, Heiko Wersing, Edgar Körner
GECCO
2006
Springer
140views Optimization» more  GECCO 2006»
15 years 1 months ago
A representational ecology for learning classifier systems
The representation used by a learning algorithm introduces a bias which is more or less well-suited to any given learning problem. It is well known that, across all possible probl...
James A. R. Marshall, Tim Kovacs