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

By Yarin Gal, Zoubin Ghahramani. 2015

12,300 citations recorded by the source corpus.

Deep learning tools have gained tremendous attention in applied machine learning. However such tools for regression and classification do not capture model uncertainty. In comparison, Bayesian models offer a mathematically grounded framework to reason about model uncertainty, but usually come with a prohibitive computational cost. In this paper we develop a new theoretical framework casting dropout training in deep neural networks (NNs) as approximate Bayesian inference in deep Gaussian processes. A direct result of this theory gives us 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 either computational complexity or test accuracy. We perform an extensive study of the properties of dropout's uncertainty. 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, and finish by using dropout's uncertainty in deep reinforcement learning.

Subfields: Artificial Intelligence, Probabilistic & Bayesian Methods

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Sergey Levine
  2. Yoshua Bengio
  3. Mohit Bansal
  4. Percy Liang
  5. Quoc V. Le
  6. Jianfeng Gao
  7. Ruslan Salakhutdinov
  8. Pieter Abbeel

In Probabilistic & Bayesian Methods

  1. Yarin Gal
  2. Richard E. Turner
  3. Zoubin Ghahramani
  4. Stefano Ermon
  5. Max Welling
  6. Yoshua Bengio
  7. José Miguel Hernández-Lobato
  8. David M. Blei

Citations in the corpus