Learning uncertainty in regression tasks by artificial neural networks

We suggest a general approach to quantification of different forms of uncertainty in regression tasks performed by artificial neural networks. It is based on the simultaneous training of two neural networks with a joint loss function. One of the networks performs predictions and the other simultaneously quantifies the uncertainty of predictions by estimating the locally averaged loss of the first one. Unlike in many classical uncertainty quantification methods, the targets are not assumed to be sampled from a probability distribution of an a priori given form. We analyze how the hyperparameters affect the learning process and, additionally, show that our method even allows for better predictions compared to standard neural networks without uncertainty counterparts. Finally, we show that particular cases of our approach include maximization of log-likelihood, assuming Gaussian or Laplace noise.