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
Posted Content
Functional Variational Bayesian Neural Networks
TL;DR: Functional variational Bayesian neural networks (fBNNs), which maximize an Evidence Lower BOund defined directly on stochastic processes, are introduced and it is proved that the KL divergence between stoChastic processes equals the supremum of marginal KL divergences over all finite sets of inputs.
Journal ArticleDOI
Neuronal diversity and convergence in a visual system developmental atlas.
Mehmet Neset Özel,Félix Simon,Shadi Jafari,Shadi Jafari,Isabel Holguera,Yen Chung Chen,Najate Benhra,Rana N. El-Danaf,Katarina Kapuralin,Jennifer Amy Malin,Nikolaos Konstantinides,Claude Desplan,Claude Desplan +12 more
TL;DR: The neuronal diversity of the Drosophila optic lobe is described throughout pupal development by single-cell sequencing, leading to the discovery of transient extrinsic neurons and a dorsoventral asymmetry of the visual circuits.
Book ChapterDOI
Human Activity Recognition Using Recurrent Neural Networks
Deepika Singh,Erinc Merdivan,Ismini Psychoula,Johannes Kropf,Sten Hanke,Matthieu Geist,Andreas Holzinger +6 more
TL;DR: A deep learning model that learns to classify human activities without using any prior knowledge is introduced and it is shown that the proposed approach outperforms the existing ones in terms of accuracy and performance.
Journal ArticleDOI
Confidence Calibration and Predictive Uncertainty Estimation for Deep Medical Image Segmentation
TL;DR: In this article, the authors compare cross-entropy loss with Dice loss in terms of segmentation quality and uncertainty estimation of fully convolutional neural networks (FCNs) for medical image segmentation.
Journal ArticleDOI
Evaluating Scalable Uncertainty Estimation Methods for Deep Learning-Based Molecular Property Prediction.
TL;DR: This paper introduces a set of quantitative criteria to capture different uncertainty aspects, and uses these criteria to compare MC-Dropout, Deep Ensembles, and bootstrapping, both theoretically in a unified framework that separates aleatoric/epistemic uncertainty and experimentally on public datasets.
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.