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
Proceedings ArticleDOI
Correlated Input-Dependent Label Noise in Large-Scale Image Classification
TL;DR: In this paper, a multivariate nor-mal distributed latent variable is used to model the aleatoric uncertainty due to label noise in the final hidden layer of a neural network classifier.
Journal ArticleDOI
Unsupervised Domain Adversarial Self-Calibration for Electromyography-Based Gesture Recognition
Ulysse Côté-Allard,Gabriel Gagnon-Turcotte,Angkoon Phinyomark,Kyrre Glette,Erik Scheme,François Laviolette,Benoit Gosselin +6 more
TL;DR: This paper proposes tackling the especially challenging task of unsupervised adaptation of sEMG signals, when multiple days have elapsed between each recording, by introducing Self-Calibrating Asynchronous Domain Adversarial Neural Network (SCADANN).
Proceedings ArticleDOI
INPREM: An Interpretable and Trustworthy Predictive Model for Healthcare
TL;DR: The proposed INPREM is designed as a linear model for interpretability while encoding non-linear relationships into the learning weights for modeling the dependencies between and within each visit and outperforms existing approaches with a significant margin.
Journal ArticleDOI
Detection of gravitational waves using Bayesian neural networks
Yu-Chiung Lin,Jiun-Huei Proty Wu +1 more
TL;DR: In this paper, a new model of Bayesian neural networks is proposed to detect the events of compact binary coalescence in the observational data of gravitational waves (GW) and identify the full length of the event duration including the inspiral stage.
Posted Content
Long-Term On-Board Prediction of People in Traffic Scenes under Uncertainty
TL;DR: In this article, the authors propose a model that jointly predicts ego motion and people trajectories over large time horizons and show that it is possible to predict trajectories at a desired time horizon and that their uncertainty estimates are informative of the prediction error.
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.