Sciweavers

2204 search results - page 7 / 441
» Agnostic active learning
Sort
View
FOCS
2008
IEEE
14 years 5 months ago
Learning Geometric Concepts via Gaussian Surface Area
We study the learnability of sets in Rn under the Gaussian distribution, taking Gaussian surface area as the “complexity measure” of the sets being learned. Let CS denote the ...
Adam R. Klivans, Ryan O'Donnell, Rocco A. Servedio
COCO
2010
Springer
149views Algorithms» more  COCO 2010»
14 years 2 months ago
The Gaussian Surface Area and Noise Sensitivity of Degree-d Polynomial Threshold Functions
Abstract. We prove asymptotically optimal bounds on the Gaussian noise sensitivity of degree-d polynomial threshold functions. These bounds translate into optimal bounds on the Gau...
Daniel M. Kane
FOCS
2009
IEEE
14 years 5 months ago
A Complete Characterization of Statistical Query Learning with Applications to Evolvability
Statistical query (SQ) learning model of Kearns is a natural restriction of the PAC learning model in which a learning algorithm is allowed to obtain estimates of statistical prop...
Vitaly Feldman
SDM
2012
SIAM
261views Data Mining» more  SDM 2012»
12 years 1 months ago
Combining Active Learning and Dynamic Dimensionality Reduction
To date, many active learning techniques have been developed for acquiring labels when training data is limited. However, an important aspect of the problem has often been neglect...
Mustafa Bilgic
CVPR
2012
IEEE
12 years 1 months ago
RALF: A reinforced active learning formulation for object class recognition
Active learning aims to reduce the amount of labels required for classification. The main difficulty is to find a good trade-off between exploration and exploitation of the lab...
Sandra Ebert, Mario Fritz, Bernt Schiele