Sciweavers

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

7

NIPS
2000

favoriteEmaildiscussreport

113views Information Technology» more NIPS 2000»

Occam's Razor

13 years 5 months ago

Download www.gatsby.ucl.ac.uk

The Bayesian paradigm apparently only sometimes gives rise to Occam's Razor; at other times very large models perform well. We give simple examples of both kinds of behaviour. The two views are reconciled when measuring complexity of functions, rather than of the machinery used to implement them. We analyze the complexity of functions for some linear in the parameter models that are equivalent to Gaussian Processes, and always find Occam's Razor at work.

Carl Edward Rasmussen, Zoubin Ghahramani

Real-time Traffic

Bayesian Paradigm | Large Models | NIPS 2000 | NIPS 2007 | Occam's Razor |

claim paper

Related Content

» Occams Razor Just Got Sharper

» The Role of Occams Razor in Knowledge Discovery

» Genetic Programming of Minimal Neural Nets Using Occams Razor

» Occams Razor Applied to Network Topology Inference

» On a Dynamical Analysis of Reinforcement Learning in Games Emergence of Occams Razor

» Slicing Spam with Occams Razor

» God Doesnt Always Shave with Occams Razor Learning When and How to Prune

» Occams Two Razors The Sharp and the Blunt

» Conditions for Occams Razor Applicability and Noise Elimination

Post Info
More Details (n/a)

Added	01 Nov 2010
Updated	01 Nov 2010
Type	Conference
Year	2000
Where	NIPS
Authors	Carl Edward Rasmussen, Zoubin Ghahramani

Comments (0)