Document Detail

General Gaussian Priors for Improved Generalization.
MedLine Citation:
PMID:  12662573     Owner:  NLM     Status:  Publisher    
We explore the dependence of performance measures, such as the generalization error and generalization consistency, on the structure and the parametrization of the prior on "rules", instanced here by the noisy linear perceptron. Using a statistical mechanics framework, we show how one may assign values to the parameters of a model for a "rule" on the basis of data instancing the rule. Information about the data, such as input distribution, noise distribution and other "rule" characteristics may be embedded in the form of general Gaussian priors for improving net performance. We examine explicitly two types of general Gaussian priors which are useful in some simple cases. We calculate the optimal values for the parameters of these priors and show their effect in modifying the most probable, MAP, values for the rules. Copyright 1996 Elsevier Science Ltd.
D Saad
Related Documents :
18782493 - Generalized negative binomial distribution: a promising statistical distribution for on...
24423323 - The incidence and prevalence of thyroid dysfunction in europe: a meta-analysis.
21041883 - Positional uncertainty of isocontours: condition analysis and probabilistic measures.
Publication Detail:
Journal Detail:
Title:  Neural networks : the official journal of the International Neural Network Society     Volume:  9     ISSN:  1879-2782     ISO Abbreviation:  Neural Netw     Publication Date:  1996 Aug 
Date Detail:
Created Date:  2003-Mar-28     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  8805018     Medline TA:  Neural Netw     Country:  -    
Other Details:
Languages:  ENG     Pagination:  937-945     Citation Subset:  -    
The University of Edinburgh, UK
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  Mechanisms of Neural Architecture for Visual Contrast and Brightness Perception.
Next Document:  An Integral Representation of Functions Using Three-layered Networks and Their Approximation Bounds.