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

Yarin Gal; Zoubin Ghahramani

doi:https://doi.org/10.48550/arxiv.1506.02142

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

2015 · arXiv (Cornell University) · 2,672 citations · 2 from inside this corpus

The source holds an abstract for this work, but its best open-access copy is under no open licence, which does not permit us to republish the text. Read it at the source below.

11 of 11 neighbouring works in this corpus. Blue is what this paper cites; orange is what cites it, and a dashed line is one neighbour citing another. Only the largest labels are drawn — every node carries its full title on hover.

this paper works it cites works citing it node size = global citations · hover for the full title

Citation edge evidence

Each row is directed from the citing work to the cited work. Source status remains readable without the interactive graph.

Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised …→Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep LearningLegacy edge — source detail unavailable
A review of uncertainty quantification in deep learning: Techniques, applications and cha…→Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep LearningLegacy edge — source detail unavailable
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning→Adam: A Method for Stochastic OptimizationLegacy edge — source detail unavailable
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning→Dropout: a simple way to prevent neural networks from overfittingLegacy edge — source detail unavailable
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning→Practical Bayesian Optimization of Machine Learning AlgorithmsLegacy edge — source detail unavailable
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning→Bayesian Learning for Neural NetworksLegacy edge — source detail unavailable
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning→Dropout as a Bayesian Approximation: Representing Model Uncertainty in\n Deep LearningLegacy edge — source detail unavailable
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning→A Practical Bayesian Framework for Backpropagation NetworksLegacy edge — source detail unavailable
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning→Probabilistic machine learning and artificial intelligenceLegacy edge — source detail unavailable
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning→Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)Legacy edge — source detail unavailable
Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning→Stochastic variational inferenceLegacy edge — source detail unavailable
Probabilistic machine learning and artificial intelligence→Bayesian Learning for Neural NetworksLegacy edge — source detail unavailable
Probabilistic machine learning and artificial intelligence→Stochastic variational inferenceLegacy edge — source detail unavailable
Dropout: a simple way to prevent neural networks from overfitting→Bayesian Learning for Neural NetworksLegacy edge — source detail unavailable
Dropout: a simple way to prevent neural networks from overfitting→Practical Bayesian Optimization of Machine Learning AlgorithmsLegacy edge — source detail unavailable
Dropout as a Bayesian Approximation: Representing Model Uncertainty in\n Deep Learning→Probabilistic machine learning and artificial intelligenceLegacy edge — source detail unavailable
Dropout as a Bayesian Approximation: Representing Model Uncertainty in\n Deep Learning→Bayesian Learning for Neural NetworksLegacy edge — source detail unavailable
Dropout as a Bayesian Approximation: Representing Model Uncertainty in\n Deep Learning→Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)Legacy edge — source detail unavailable
Dropout as a Bayesian Approximation: Representing Model Uncertainty in\n Deep Learning→Dropout: a simple way to prevent neural networks from overfittingLegacy edge — source detail unavailable
Dropout as a Bayesian Approximation: Representing Model Uncertainty in\n Deep Learning→A Practical Bayesian Framework for Backpropagation NetworksLegacy edge — source detail unavailable
Dropout as a Bayesian Approximation: Representing Model Uncertainty in\n Deep Learning→Practical Bayesian Optimization of Machine Learning AlgorithmsLegacy edge — source detail unavailable
Dropout as a Bayesian Approximation: Representing Model Uncertainty in\n Deep Learning→Stochastic variational inferenceLegacy edge — source detail unavailable
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised …→Adam: A Method for Stochastic OptimizationLegacy edge — source detail unavailable
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised …→Dropout: a simple way to prevent neural networks from overfittingLegacy edge — source detail unavailable
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised …→Dropout as a Bayesian Approximation: Representing Model Uncertainty in\n Deep LearningLegacy edge — source detail unavailable
A review of uncertainty quantification in deep learning: Techniques, applications and cha…→Bayesian Learning for Neural NetworksLegacy edge — source detail unavailable
A review of uncertainty quantification in deep learning: Techniques, applications and cha…→Dropout: a simple way to prevent neural networks from overfittingLegacy edge — source detail unavailable
A review of uncertainty quantification in deep learning: Techniques, applications and cha…→Practical Bayesian Optimization of Machine Learning AlgorithmsLegacy edge — source detail unavailable
A review of uncertainty quantification in deep learning: Techniques, applications and cha…→Dropout as a Bayesian Approximation: Representing Model Uncertainty in\n Deep LearningLegacy edge — source detail unavailable

What this paper cites, inside the corpus

Paper	Year	Cited
Adam: A Method for Stochastic Optimization	2014	84,698
Dropout: a simple way to prevent neural networks from overfitting	2014	34,236
Practical Bayesian Optimization of Machine Learning Algorithms	2012	5,674
Bayesian Learning for Neural Networks	1996	4,397
Dropout as a Bayesian Approximation: Representing Model Uncertainty in\n Deep Learning	2015	4,187
A Practical Bayesian Framework for Backpropagation Networks	1992	2,962
Probabilistic machine learning and artificial intelligence	2015	2,031
Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)	2005	1,859
Stochastic variational inference	2013	1,480

What cites it, inside the corpus

Paper	Year	Cited
Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised …	2018	2,873
A review of uncertainty quantification in deep learning: Techniques, applications and cha…	2021	2,644

Links

Download BibTeX · Download RIS · DOI · Open access copy · OpenAlex record

Topics

Gaussian Processes and Bayesian Inference	Computer Science
Adversarial Robustness in Machine Learning	Computer Science
Machine Learning and Data Classification	Computer Science

Is this record sound?

complete

Nothing in this record contradicts itself and no field we check is missing.

supports2 author record(s) attached.
supports40 reference(s) recorded.
neutralThe DOI carries no year to check against.
supportsA title is present.

Provenance

Everything above was read from one stored OpenAlex payload, fetched 2026-09-04T03:58:48+00:00.

sha256 46f669157f96ea35…