中文
相关论文

相关论文: Deep Ensembles Secretly Perform Empirical Bayes

200 篇论文

Understanding the uncertainty of a neural network's (NN) predictions is essential for many purposes. The Bayesian framework provides a principled approach to this, however applying it to NNs is challenging due to large numbers of parameters…

机器学习 · 统计学 2020-02-27 Tim Pearce , Felix Leibfried , Alexandra Brintrup , Mohamed Zaki , Andy Neely

Bayesian neural networks (BNNs) augment deep networks with uncertainty quantification by Bayesian treatment of the network weights. However, such models face the challenge of Bayesian inference in a high-dimensional and usually…

机器学习 · 计算机科学 2021-03-30 Zhijie Deng , Yucen Luo , Jun Zhu , Bo Zhang

Deep ensembles have emerged as a powerful technique for improving predictive performance and enhancing model robustness across various applications by leveraging model diversity. However, traditional deep ensemble methods are often…

Bayesian Neural Networks (BNNs) often improve model calibration and predictive uncertainty quantification compared to point estimators such as maximum-a-posteriori (MAP). Similarly, deep ensembles (DEs) are also known to improve…

机器学习 · 计算机科学 2025-03-18 Mikkel Jordahn , Jonas Vestergaard Jensen , Mikkel N. Schmidt , Michael Riis Andersen

Ensembles of neural networks achieve superior performance compared to stand-alone networks in terms of accuracy, uncertainty calibration and robustness to dataset shift. \emph{Deep ensembles}, a state-of-the-art method for uncertainty…

机器学习 · 计算机科学 2022-02-23 Sheheryar Zaidi , Arber Zela , Thomas Elsken , Chris Holmes , Frank Hutter , Yee Whye Teh

Neural network potentials (NNPs) combine the computational efficiency of classical interatomic potentials with the high accuracy and flexibility of the ab initio methods used to create the training set, but can also result in unphysical…

材料科学 · 物理学 2022-01-24 Leonid Kahle , Federico Zipoli

Deep Bayesian neural networks (BNNs) are a powerful tool, though computationally demanding, to perform parameter estimation while jointly estimating uncertainty around predictions. BNNs are typically implemented using arbitrary…

机器学习 · 计算机科学 2020-05-12 Daniele Silvestro , Tobias Andermann

Generalization is essential for deep learning. In contrast to previous works claiming that Deep Neural Networks (DNNs) have an implicit regularization implemented by the stochastic gradient descent, we demonstrate explicitly Bayesian…

机器学习 · 计算机科学 2019-10-23 Xinjie Lan , Kenneth E. Barner

Artificial neural networks have been successfully applied to a variety of machine learning tasks, including image recognition, semantic segmentation, and machine translation. However, few studies fully investigated ensembles of artificial…

机器学习 · 统计学 2017-04-07 Cheng Ju , Aurélien Bibaut , Mark J. van der Laan

Deep neural networks (DNN) are versatile parametric models utilised successfully in a diverse number of tasks and domains. However, they have limitations---particularly from their lack of robustness and over-sensitivity to out of…

机器学习 · 统计学 2020-01-01 John Mitros , Brian Mac Namee

We show that ensembles of deep neural networks, called deep ensembles, can be used to perform quantum parameter estimation while also providing a means for quantifying uncertainty in parameter estimates, which is a key advantage of using…

量子物理 · 物理学 2026-03-09 Amanuel Anteneh

Modern neural networks tend to be overconfident on unseen, noisy or incorrectly labelled data and do not produce meaningful uncertainty measures. Bayesian deep learning aims to address this shortcoming with variational approximations (such…

机器学习 · 统计学 2018-05-28 Nick Pawlowski , Andrew Brock , Matthew C. H. Lee , Martin Rajchl , Ben Glocker

Quantifying the uncertainty in the output of a neural network is essential for deployment in scientific or engineering applications where decisions must be made under limited or noisy data. Bayesian neural networks (BNNs) provide a…

机器学习 · 统计学 2026-03-10 Alex Alberts , Ilias Bilionis

Deep Neural Networks (DNNs) are powerful tools for various computer vision tasks, yet they often struggle with reliable uncertainty quantification - a critical requirement for real-world applications. Bayesian Neural Networks (BNN) are…

机器学习 · 计算机科学 2023-12-27 Gianni Franchi , Olivier Laurent , Maxence Leguéry , Andrei Bursuc , Andrea Pilzer , Angela Yao

Bayesian Neural Networks (BNNs) offer a principled and natural framework for proper uncertainty quantification in the context of deep learning. They address the typical challenges associated with conventional deep learning methods, such as…

统计计算 · 统计学 2024-11-13 Zahra Moslemi , Yang Meng , Shiwei Lan , Babak Shahbaba

Obtaining labeled data for machine learning tasks can be prohibitively expensive. Active learning mitigates this issue by exploring the unlabeled data space and prioritizing the selection of data that can best improve the model performance.…

机器学习 · 计算机科学 2021-04-21 Vineeth Rakesh , Swayambhoo Jain

We present a novel approach for training deep neural networks in a Bayesian way. Classical, i.e. non-Bayesian, deep learning has two major drawbacks both originating from the fact that network parameters are considered to be deterministic.…

机器学习 · 统计学 2019-03-11 Konstantin Posch , Jan Steinbrener , Jürgen Pilz

We show that training a deep network using batch normalization is equivalent to approximate inference in Bayesian models. We further demonstrate that this finding allows us to make meaningful estimates of the model uncertainty using…

机器学习 · 统计学 2018-07-17 Mattias Teye , Hossein Azizpour , Kevin Smith

Predictive uncertainty quantification is crucial for reliable decision-making in various applied domains. Bayesian neural networks offer a powerful framework for this task. However, defining meaningful priors and ensuring computational…

机器学习 · 计算机科学 2024-04-30 Yijia Liu , Xiao Wang

Deep neural network ensembles are powerful tools for uncertainty quantification, which have recently been re-interpreted from a Bayesian perspective. However, current methods inadequately leverage second-order information of the loss…

机器学习 · 统计学 2024-11-05 Klemens Flöge , Mohammed Abdul Moeed , Vincent Fortuin