We analyze how data with uncertain or missing input features can be incorporated into the training of a neural network. The general solution requires a weighted integration over the unknown or uncertain input although computationally cheaper closed-form solutions can be found for certain Gaussian Basis Function (GBF) networks. We also discuss cases in which heuristical solutions such as substituting the mean of an unknown input can be harmful.

We analyze how data with uncertain or missing input features can be incorporated into the training of a neural network. The general solutionrequires a weighted integration over the unknown or uncertain input although computationally cheaper closed-form solutions canbe found for certain Gaussian Basis Function (GBF) networks. We also discuss cases in which heuristical solutions such as substituting the mean of an unknown input can be harmful.