@inbook{a1a7cf36d67847c5b6c46823387eb844,
title = "On the relationship between Bayesian error bars and the input data density",
abstract = "We investigate the dependence of Bayesian error bars on the distribution of data in input space. For generalized linear regression models we derive an upper bound on the error bars which shows that, in the neighbourhood of the data points, the error bars are substantially reduced from their prior values. For regions of high data density we also show that the contribution to the output variance due to the uncertainty in the weights can exhibit an approximate inverse proportionality to the probability density. Empirical results support these conclusions.",
keywords = "Bayes methods, neural nets, prediction theory, ayesian error bars, error bars, high data densit, input data density, linear regression models, probability density",
author = "Williams, {C. K. I.} and C. Qazaz and Bishop, {Christopher M.} and H. Zhu",
note = "{\textcopyright}1995 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.; Proc. Fourth International Conference on Artificial Neural Networks ; Conference date: 26-06-1995 Through 26-06-1995",
year = "1995",
month = jun,
day = "26",
language = "English",
isbn = "0852966415",
series = "IEE Conference Publication",
publisher = "IEEE",
pages = "160--165",
booktitle = "Fourth International Conference on Artificial Neural Networks, 1995",
address = "United States",
}