Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

Deep learning has gained tremendous attention in applied machine learning. However such tools for regression and classification do not capture model uncertainty. Bayesian models offer a mathematically grounded framework to reason about model uncertainty, but usually come with a prohibitive computational cost. We show that dropout in neural networks (NNs) can be cast as a Bayesian approximation. As a direct result we obtain tools to model uncertainty with dropout NNs -- extracting information from existing models that has been thrown away so far. This mitigates the problem of representing uncertainty in deep learning without sacrificing computational complexity or test accuracy. We perform an extensive study of the dropout uncertainty properties. Various network architectures and non-linearities are assessed on tasks of regression and classification, using MNIST as an example. We show a considerable improvement in predictive log-likelihood and RMSE compared to existing state-of-the-art methods. We finish by using dropout uncertainty in a Bayesian pipeline, with deep reinforcement learning as a practical task.