Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

41

NIPS
2001

favoriteEmaildiscussreport

152views Information Technology» more NIPS 2001»

A Variational Approach to Learning Curves

14 years 10 days ago

A Variational Approach to Learning Curves

Download ki.cs.tu-berlin.de

We combine the replica approach from statistical physics with a variational approach to analyze learning curves analytically. We apply the method to Gaussian process regression. As a main result we derive approximative relations between empirical error measures, the generalization error and the posterior variance.

Dörthe Malzahn, Manfred Opper

Real-time Traffic

Gaussian Process Regression | NIPS 2001 | NIPS 2007 | Replica Approach | Variational Approach |

claim paper

Related Content

» Fairness Criteria for Algebraic Curves

» A Shape Constrained Curve Approximation Method for Styling Surfaces Modeling

» A curve evolutionbased variational approach to simultaneous image restoration and segmenta...

» A variational approach to spline curves on surfaces

» A Variational Approach for Object Contour Tracking

» Precisionrecall operating characteristic PROC curves in imprecise environments

» Democratic approximation of lexicographic preference models

» Variational optimal control technique for the tracking of deformable objects

» Understanding the scalability of Bayesian network inference using clique tree growth curve...

Post Info
More Details (n/a)

Added	31 Oct 2010
Updated	31 Oct 2010
Type	Conference
Year	2001
Where	NIPS
Authors	Dörthe Malzahn, Manfred Opper

Comments (0)