Related papers: Uncertainty Estimation by Fisher Information-based…

Uncertainty-based deep learning models have attracted a great deal of interest for their ability to provide accurate and reliable predictions. Evidential deep learning stands out achieving remarkable performance in detecting…

Assessing the predictive uncertainty of deep neural networks is crucial for safety-related applications of deep learning. Although Bayesian deep learning offers a principled framework for estimating model uncertainty, the common approaches…

Deep Ensembles, as a type of Bayesian Neural Networks, can be used to estimate uncertainty on the prediction of multiple neural networks by collecting votes from each network and computing the difference in those predictions. In this paper,…

Intelligibility and accurate uncertainty estimation are crucial for reliable decision-making. In this paper, we propose EviNAM, an extension of evidential learning that integrates the interpretability of Neural Additive Models (NAMs) with…

In this work we aim to obtain computationally-efficient uncertainty estimates with deep networks. For this, we propose a modified knowledge distillation procedure that achieves state-of-the-art uncertainty estimates both for in and…

Uncertainty estimation in deep learning has become a leading research field in medical image analysis due to the need for safe utilisation of AI algorithms in clinical practice. Most approaches for uncertainty estimation require sampling…

Multi-view evidential learning aims to integrate information from multiple views to improve prediction performance and provide trustworthy uncertainty esitimation. Most previous methods assume that view-specific evidence learning is…

Reliably assessing model confidence in deep learning and predicting errors likely to be made are key elements in providing safety for model deployment, in particular for applications with dire consequences. In this paper, it is first shown…

The Fisher information matrix (FIM) is a key quantity in statistics as it is required for example for evaluating asymptotic precisions of parameter estimates, for computing test statistics or asymptotic distributions in statistical testing,…

Neural networks predictions are unreliable when the input sample is out of the training distribution or corrupted by noise. Being able to detect such failures automatically is fundamental to integrate deep learning algorithms into robotics.…

Although the existing uncertainty-based semi-supervised medical segmentation methods have achieved excellent performance, they usually only consider a single uncertainty evaluation, which often fails to solve the problem related to…

Rigorous statistical methods, including parameter estimation with accompanying uncertainties, underpin the validity of scientific discovery, especially in the natural sciences. With increasingly complex data models such as deep learning…

We present the fundamental theory and implementation guidelines underlying Evidential Physics-Informed Neural Network (E-PINN) -- a novel class of uncertainty-aware PINN. It leverages the marginal distribution loss function of evidential…

Traditional deep neural nets (NNs) have shown the state-of-the-art performance in the task of classification in various applications. However, NNs have not considered any types of uncertainty associated with the class probabilities to…

In automatic emotion recognition (AER), labels assigned by different human annotators to the same utterance are often inconsistent due to the inherent complexity of emotion and the subjectivity of perception. Though deterministic labels…

Uncertainty quantification (UQ) in scientific machine learning is increasingly critical as neural networks are widely adopted to tackle complex problems across diverse scientific disciplines. For physics-informed neural networks (PINNs), a…

Deep learning (DL) models are popular across various domains due to their remarkable performance and efficiency. However, their effectiveness relies heavily on large amounts of labeled data, which are often time-consuming and…

Federated learning facilitates the collaborative learning of a global model across multiple distributed medical institutions without centralizing data. Nevertheless, the expensive cost of annotation on local clients remains an obstacle to…

Linking textual values in tabular data to their corresponding entities in a Knowledge Base is a core task across a variety of data integration and enrichment applications. Although Large Language Models (LLMs) have shown State-of-The-Art…

Reliable radar pulse classification is essential in Electromagnetic Warfare for situational awareness and decision support. Deep Neural Networks have shown strong performance in radar pulse and RF emitter recognition; however, on their own…