Estimating the mean and variance of the target probability distribution
DA Nix, AS Weigend - … of 1994 ieee international conference on …, 1994 - ieeexplore.ieee.org
DA Nix, AS Weigend
Proceedings of 1994 ieee international conference on neural …, 1994•ieeexplore.ieee.orgIntroduces a method that estimates the mean and the variance of the probability distribution
of the target as a function of the input, given an assumed target error-distribution model.
Through the activation of an auxiliary output unit, this method provides a measure of the
uncertainty of the usual network output for each input pattern. The authors derive the cost
function and weight-update equations for the example of a Gaussian target error distribution,
and demonstrate the feasibility of the network on a synthetic problem where the true input …
of the target as a function of the input, given an assumed target error-distribution model.
Through the activation of an auxiliary output unit, this method provides a measure of the
uncertainty of the usual network output for each input pattern. The authors derive the cost
function and weight-update equations for the example of a Gaussian target error distribution,
and demonstrate the feasibility of the network on a synthetic problem where the true input …
Introduces a method that estimates the mean and the variance of the probability distribution of the target as a function of the input, given an assumed target error-distribution model. Through the activation of an auxiliary output unit, this method provides a measure of the uncertainty of the usual network output for each input pattern. The authors derive the cost function and weight-update equations for the example of a Gaussian target error distribution, and demonstrate the feasibility of the network on a synthetic problem where the true input-dependent noise level is known.<>
ieeexplore.ieee.org