Open AccessProceedings Article
Dropout as a Bayesian approximation: representing model uncertainty in deep learning
Yarin Gal,Zoubin Ghahramani +1 more
- pp 1050-1059
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
Book ChapterDOI
FuseNet: Incorporating Depth into Semantic Segmentation via Fusion-Based CNN Architecture
TL;DR: This paper proposes an encoder-decoder type network, where the encoder part is composed of two branches of networks that simultaneously extract features from RGB and depth images and fuse depth features into the RGB feature maps as the network goes deeper.
Journal ArticleDOI
Interactive Medical Image Segmentation Using Deep Learning With Image-Specific Fine Tuning
Guotai Wang,Wenqi Li,Maria A. Zuluaga,Rosalind Pratt,Premal A. Patel,Michael Aertsen,Tom Doel,Anna L. David,Jan Deprest,Sebastien Ourselin,Tom Vercauteren +10 more
TL;DR: A novel deep learning-based interactive segmentation framework by incorporating CNNs into a bounding box and scribble-based segmentation pipeline and proposing a weighted loss function considering network and interaction-based uncertainty for the fine tuning is proposed.
Posted Content
Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm
Qiang Liu,Dilin Wang +1 more
TL;DR: This paper proposed a variational inference algorithm that forms a natural counterpart of gradient descent for optimization, which iteratively transports a set of particles to match the target distribution by applying a form of functional gradient descent that minimizes the KL divergence.
Posted Content
WILDS: A Benchmark of in-the-Wild Distribution Shifts
Pang Wei Koh,Shiori Sagawa,Henrik Marklund,Sang Michael Xie,Marvin Zhang,Akshay Balsubramani,Weihua Hu,Michihiro Yasunaga,Richard Lanas Phillips,Irena Gao,Tony Lee,Etienne David,Ian Stavness,Wei Guo,Berton A. Earnshaw,Imran S. Haque,Sara Beery,Jure Leskovec,Anshul Kundaje,Emma Pierson,Sergey Levine,Chelsea Finn,Percy Liang +22 more
TL;DR: WILDS is presented, a benchmark of in-the-wild distribution shifts spanning diverse data modalities and applications, and is hoped to encourage the development of general-purpose methods that are anchored to real-world distribution shifts and that work well across different applications and problem settings.
Journal ArticleDOI
Physics-constrained deep learning for high-dimensional surrogate modeling and uncertainty quantification without labeled data
TL;DR: This paper provides a methodology that incorporates the governing equations of the physical model in the loss/likelihood functions of the model predictive density and the reference conditional density as a minimization problem of the reverse Kullback-Leibler (KL) divergence.
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.