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
A survey on policy search algorithms for learning robot controllers in a handful of trials
Konstantinos Chatzilygeroudis,Vassilis Vassiliades,Freek Stulp,Sylvain Calinon,Jean-Baptiste Mouret +4 more
TL;DR: In this paper, the authors focus on the extreme other end of the spectrum: how can a robot adapt with only a handful of trials (a dozen and a few minutes) and refer to this challenge as "micro-data reinforcement learning".
Journal ArticleDOI
Indoor Scene Understanding in 2.5/3D for Autonomous Agents: A Survey
TL;DR: This survey paper provides a comprehensive background to the developed techniques according to a taxonomy based on the scene understanding tasks, and summarizes the performance metrics used for evaluation in different tasks and a quantitative comparison among the recent state-of-the-art techniques.
Posted Content
Consistency-based Semi-supervised Active Learning: Towards Minimizing Labeling Cost
TL;DR: A consistency-based sample selection metric that is coherent with the training objective such that the selected samples are effective at improving model performance and a measure that is empirically correlated with the AL target loss and is potentially useful for determining the proper starting point of learning-based AL methods.
Book ChapterDOI
Iris Segmentation Using Fully Convolutional Encoder--Decoder Networks
Ehsaneddin Jalilian,Andreas Uhl +1 more
TL;DR: This chapter considers the application of Fully Convolutional Encoder–Decoder Networks (FCEDNs) for iris segmentation and proposes three types of FCEDN architectures for segmentation of the iris in the images, obtained from five different datasets, acquired under different scenarios.
Proceedings ArticleDOI
3D Semi-Supervised Learning with Uncertainty-Aware Multi-View Co-Training
Yingda Xia,Fengze Liu,Dong Yang,Jinzheng Cai,Lequan Yu,Zhuotun Zhu,Daguang Xu,Alan L. Yuille,Holger R. Roth +8 more
TL;DR: In this article, an uncertainty-aware multi-view co-training (UMCT) was proposed to address semi-supervised learning on 3D data, such as volumetric data from medical imaging.
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.