中文
相关论文

相关论文: On the Validity of Bayesian Neural Networks for Un…

200 篇论文

When incorporating deep neural networks into robotic systems, a major challenge is the lack of uncertainty measures associated with their output predictions. Methods for uncertainty estimation in the output of deep object detectors (DNNs)…

计算机视觉与模式识别 · 计算机科学 2019-09-17 Ali Harakeh , Michael Smart , Steven L. Waslander

In many applications with real-world consequences, it is crucial to develop reliable uncertainty estimation for the predictions made by the AI decision systems. Targeting at the goal of estimating uncertainty, various deep neural network…

机器学习 · 计算机科学 2022-10-13 Huimin Zeng , Zhenrui Yue , Yang Zhang , Ziyi Kou , Lanyu Shang , Dong Wang

Deep Neural Networks are, from a physical perspective, graphs whose `links` and `vertices` iteratively process data and solve tasks sub-optimally. We use Complex Network Theory (CNT) to represents Deep Neural Networks (DNNs) as directed…

机器学习 · 计算机科学 2022-09-14 Emanuele La Malfa , Gabriele La Malfa , Claudio Caprioli , Giuseppe Nicosia , Vito Latora

Deep learning (DL) models have received particular attention in medical imaging due to their promising pattern recognition capabilities. However, Deep Neural Networks (DNNs) require a huge amount of data, and because of the lack of…

图像与视频处理 · 电气工程与系统科学 2021-07-27 Donya Khaledyan , AmirReza Tajally , Ali Sarkhosh , Afshar Shamsi , Hamzeh Asgharnezhad , Abbas Khosravi , Saeid Nahavandi

Bayesian Neural Networks (BNNs) offer a mathematically grounded framework to quantify the uncertainty of model predictions but come with a prohibitive computation cost for both training and inference. In this work, we show a novel network…

机器学习 · 计算机科学 2022-02-10 Duo Wang , Yiren Zhao , Ilia Shumailov , Robert Mullins

Deep neural networks (DNNs) have achieved tremendous success in computer vision, natural language processing, and scientific and engineering domains. However, DNNs can make unexpected, incorrect, yet overconfident predictions, leading to…

机器学习 · 计算机科学 2025-12-16 Wenchong He , Zhe Jiang , Tingsong Xiao , Zelin Xu , Yukun Li

Quantifying uncertainty in neural networks is a highly relevant problem which is essential to many applications. The two predominant paradigms to tackle this task are Bayesian neural networks (BNNs) and deep ensembles. Despite some…

机器学习 · 计算机科学 2025-01-31 Gabriel Loaiza-Ganem , Valentin Villecroze , Yixin Wang

We introduce a probabilistic robustness measure for Bayesian Neural Networks (BNNs), defined as the probability that, given a test point, there exists a point within a bounded set such that the BNN prediction differs between the two. Such a…

机器学习 · 计算机科学 2019-03-06 Luca Cardelli , Marta Kwiatkowska , Luca Laurenti , Nicola Paoletti , Andrea Patane , Matthew Wicker

In this paper, we describe a Bayesian deep neural network (DNN) for predicting FreeSurfer segmentations of structural MRI volumes, in minutes rather than hours. The network was trained and evaluated on a large dataset (n = 11,480), obtained…

Deep Neural Networks (DNNs) have performed admirably in classification tasks. However, the characterization of their classification uncertainties, required for certain applications, has been lacking. In this work, we investigate the issue…

机器学习 · 计算机科学 2023-11-28 Yu Pan , Kwo-Sen Kuo , Michael L. Rilee , Hongfeng Yu

Deep Neural Networks (DNNs) are rapidly gaining popularity in a variety of important domains. Formally, DNNs are complicated vector-valued functions which come in a variety of sizes and applications. Unfortunately, modern DNNs have been…

机器学习 · 计算机科学 2021-01-12 Matthew Sotoudeh , Aditya V. Thakur

Bayesian Neural Networks (BNNs) have become one of the promising approaches for uncertainty estimation due to the solid theorical foundations. However, the performance of BNNs is affected by the ability of catching uncertainty. Instead of…

机器学习 · 计算机科学 2024-04-15 Shiyu Shen , Bin Pan , Tianyang Shi , Tao Li , Zhenwei Shi

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

Deep learning has been successfully applied to the segmentation of 3D Computed Tomography (CT) scans. Establishing the credibility of these segmentations requires uncertainty quantification (UQ) to identify untrustworthy predictions. Recent…

图像与视频处理 · 电气工程与系统科学 2020-04-03 Tyler LaBonte , Carianne Martinez , Scott A. Roberts

When fine-tuning Deep Neural Networks (DNNs) to new data, DNNs are prone to overwriting network parameters required for task-specific functionality on previously learned tasks, resulting in a loss of performance on those tasks. We propose…

机器学习 · 计算机科学 2025-01-22 Christopher Angelini , Nidhal Bouaynaya

While deep neural networks have become the go-to approach in computer vision, the vast majority of these models fail to properly capture the uncertainty inherent in their predictions. Estimating this predictive uncertainty can be crucial,…

机器学习 · 计算机科学 2020-04-08 Fredrik K. Gustafsson , Martin Danelljan , Thomas B. Schön

Modern neural networks have found to be miscalibrated in terms of confidence calibration, i.e., their predicted confidence scores do not reflect the observed accuracy or precision. Recent work has introduced methods for post-hoc confidence…

计算机视觉与模式识别 · 计算机科学 2021-09-22 Fabian Küppers , Jan Kronenberger , Jonas Schneider , Anselm Haselhoff

Deep neural networks (DNNs) are machine learning algorithms that have revolutionised computer vision due to their remarkable successes in tasks like object classification and segmentation. The success of DNNs as computer vision algorithms…

计算机视觉与模式识别 · 计算机科学 2023-05-29 Felix A. Wichmann , Robert Geirhos

This work develops rigorous theoretical basis for the fact that deep Bayesian neural network (BNN) is an effective tool for high-dimensional variable selection with rigorous uncertainty quantification. We develop new Bayesian non-parametric…

机器学习 · 统计学 2019-12-04 Jeremiah Zhe Liu

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