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
Sequential Graph Convolutional Network for Active Learning
TL;DR: In this article, a pool-based active learning framework constructed on a sequential graph convolutional network (GCN) is proposed, where each image feature from a pool of data represents a node in the graph and the edges encode their similarities.
Proceedings ArticleDOI
Backdooring Convolutional Neural Networks via Targeted Weight Perturbations
Jacob Dumford,Walter J. Scheirer +1 more
TL;DR: In this paper, a white-box backdoor attack that exploits a vulnerability of convolutional neural networks (CNNs) is presented. But, unlike other commercial technologies such as operating systems and network devices, deep learning-based facial recognition algorithms are not presently designed with security requirements or audited for security vulnerabilities before deployment.
Proceedings ArticleDOI
Improving Confidence Estimates for Unfamiliar Examples
Zhizhong Li,Derek Hoiem +1 more
TL;DR: In this article, the authors compare and evaluate several methods to improve confidence estimates for unfamiliar and familiar samples, including confidence calibration, ensembles, distillation, and a Bayesian model.
Posted Content
Learnable Bernoulli Dropout for Bayesian Deep Learning
TL;DR: Li et al. as discussed by the authors proposed learnable Bernoulli dropout (LBD), a new model-agnostic dropout scheme that considers the dropout rates as parameters jointly optimized with other model parameters.
Book ChapterDOI
Detecting When Pre-trained nnU-Net Models Fail Silently for Covid-19 Lung Lesion Segmentation
Camila González,Karol Gotkowski,Andreas M. Bucher,Ricarda Fischbach,Isabel Kaltenborn,Anirban Mukhopadhyay +5 more
TL;DR: In this paper, a lightweight OOD detection method that exploits the Mahalanobis distance in the feature space is proposed, which can be seamlessly integrated into state-of-the-art segmentation pipelines without requiring changes in model architecture or training procedure and can therefore be used to assess the suitability of pre-trained models to new data.
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.