Open AccessProceedings Article
Dropout as a Bayesian approximation: representing model uncertainty in deep learning
Yarin Gal,Zoubin Ghahramani +1 more
- pp 1050-1059
Reads0
Chats0
TLDR
A new theoretical framework is developed casting dropout training in deep neural networks (NNs) as approximate Bayesian inference in deep Gaussian processes, which mitigates the problem of representing uncertainty in deep learning without sacrificing either computational complexity or test accuracy.Abstract:
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 nonlinearities 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.read more
Citations
More filters
Journal ArticleDOI
BayesCap: A Bayesian Approach to Brain Tumor Classification Using Capsule Networks
TL;DR: A Bayesian CapsNet framework is proposed, referred to as the $\text{BayesCap}$, that can provide not only the mean predictions, but also entropy as a measure of prediction uncertainty, to improve the accuracy and interpretability of the network.
Journal ArticleDOI
Petrophysical properties prediction from prestack seismic data using convolutional neural networksPetrophysical properties using CNNs
Vishal Das,Tapan Mukerji +1 more
TL;DR: In this paper, the authors used CNNs to obtain petrophysical properties in the depth domain from prestack seismic data in the time domain and compared end-to-end workflows.
Posted Content
Adversarial Examples on Object Recognition: A Comprehensive Survey
TL;DR: The hypotheses behind their existence, the methods used to construct or protect against them, and the capacity to transfer adversarial examples between different machine learning models are introduced to provide a comprehensive and self-contained survey of this growing field of research.
Journal ArticleDOI
Missing well log prediction using convolutional long short-term memory network
TL;DR: The method is examined on sonic log prediction and can produce an accurate prediction of sonic logs from gamma-ray, density, and neutron porosity logs and outputs the uncertainties facilitated by dropout layers and Monte Carlo sampling at inference time.
Posted Content
Test Selection for Deep Learning Systems
TL;DR: An in-depth empirical comparison of a set of test selection metrics based on the notion of model uncertainty, which shows that uncertainty-based metrics have a strong ability to identify misclassified inputs, being three times stronger than surprise adequacy and outperforming coverage-related metrics.
References
More filters
Proceedings Article
Adam: A Method for Stochastic Optimization
Diederik P. Kingma,Jimmy Ba +1 more
TL;DR: This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework.
Journal ArticleDOI
Gradient-based learning applied to document recognition
Yann LeCun,Léon Bottou,Léon Bottou,Yoshua Bengio,Yoshua Bengio,Yoshua Bengio,Patrick Haffner +6 more
TL;DR: In this article, a graph transformer network (GTN) is proposed for handwritten character recognition, which can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters.
Journal Article
Dropout: a simple way to prevent neural networks from overfitting
TL;DR: It is shown that dropout improves the performance of neural networks on supervised learning tasks in vision, speech recognition, document classification and computational biology, obtaining state-of-the-art results on many benchmark data sets.
Journal ArticleDOI
Human-level control through deep reinforcement learning
Volodymyr Mnih,Koray Kavukcuoglu,David Silver,Andrei Rusu,Joel Veness,Marc G. Bellemare,Alex Graves,Martin Riedmiller,Andreas K. Fidjeland,Georg Ostrovski,Stig Petersen,Charles Beattie,Amir Sadik,Ioannis Antonoglou,Helen King,Dharshan Kumaran,Daan Wierstra,Shane Legg,Demis Hassabis +18 more
TL;DR: This work bridges the divide between high-dimensional sensory inputs and actions, resulting in the first artificial agent that is capable of learning to excel at a diverse array of challenging tasks.
Proceedings Article
Auto-Encoding Variational Bayes
Diederik P. Kingma,Max Welling +1 more
TL;DR: A stochastic variational inference and learning algorithm that scales to large datasets and, under some mild differentiability conditions, even works in the intractable case is introduced.