相关论文: SweiNet: Deep Learning Based Uncertainty Quantific…

Deep neural networks (DNNs) have proven to be powerful predictors and are widely used for various tasks. Credible uncertainty estimation of their predictions, however, is crucial for their deployment in many risk-sensitive applications. In…

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…

Deep neural networks (DNNs) are famous for their high prediction accuracy, but they are also known for their black-box nature and poor interpretability. We consider the problem of variable selection, that is, selecting the input variables…

Several neurodegenerative diseases involve the accumulation of cellular DNA damage. Comet assays are a popular way of estimating the extent of DNA damage. Current literature on the use of deep learning to quantify DNA damage presents an…

This study considers the joint location and velocity estimation of UE and scatterers in a three-dimensional mmWave CRAN architecture. Several existing works have achieved satisfactory results with neural networks (NNs) for localization.…

I propose a novel framework that integrates stochastic differential equations (SDEs) with deep generative models to improve uncertainty quantification in machine learning applications involving structured and temporal data. This approach,…

Medical image segmentation is a difficult but important task for many clinical operations such as cardiac bi-ventricular volume estimation. More recently, there has been a shift to utilizing deep learning and fully convolutional neural…

During training, the weights of a Deep Neural Network (DNN) are optimized from a random initialization towards a nearly optimum value minimizing a loss function. Only this final state of the weights is typically kept for testing, while the…

Despite the fact that our physical observations can often be described by derived physical laws, such as the wave equation, in many cases, we observe data that do not match the laws or have not been described physically yet. Therefore…

Medical instrument segmentation in 3D ultrasound is essential for image-guided intervention. However, to train a successful deep neural network for instrument segmentation, a large number of labeled images are required, which is expensive…

We propose a novel deep neural network (DNN) based approximation architecture to learn estimates of measurements. We detail an algorithm that enables training of the DNN. The DNN estimator only uses measurements, if and when they are…

Quality assessment of prenatal ultrasonography is essential for the screening of fetal central nervous system (CNS) anomalies. The interpretation of fetal brain structures is highly subjective, expertise-driven, and requires years of…

Purpose: Accurate segmentation of glioma subregions in multi-parametric MRI (MP-MRI) is essential for diagnosis and treatment planning but remains challenging due to tumor heterogeneity and ambiguous boundaries. This study proposes an…

Uncertainty-quantification methods are applied to estimate the confidence of deep-neural-networks classifiers over their predictions. However, most widely used methods are known to be overconfident. We address this problem by developing an…

Single-pixel imaging (SPI) has the advantages of high-speed acquisition over a broad wavelength range and system compactness, which are difficult to achieve by conventional imaging sensors. However, a common challenge is low image quality…

Uncertainty quantification is vital for safety-critical Deep Learning applications like medical image segmentation. We introduce BA U-Net, an uncertainty-aware model for MRI segmentation that integrates Bayesian Neural Networks with…

Modeling of strong gravitational lenses is a necessity for further applications in astrophysics and cosmology. Especially with the large number of detections in current and upcoming surveys such as the Rubin Legacy Survey of Space and Time…

Computer vision leveraging deep learning has achieved significant success in the last decade. Despite the promising performance of the existing deep models in the recent literature, the extent of models' reliability remains unknown.…

The high dynamics and heterogeneous interactions in the complicated urban systems have raised the issue of uncertainty quantification in spatiotemporal human mobility, to support critical decision-makings in risk-aware web applications such…

Neural network ensembles, such as Bayesian neural networks (BNNs), have shown success in the areas of uncertainty estimation and robustness. However, a crucial challenge prohibits their use in practice. BNNs require a large number of…