English
Related papers

Related papers: Interpretable epistemic uncertainty decomposition …

200 papers

The need to rapidly solve PDEs in engineering design workflows has spurred the rise of neural surrogate models. In particular, neural operator models provide a discretization-invariant surrogate by retaining the infinite-dimensional,…

Machine Learning · Computer Science 2026-02-12 Yash Patel , Ambuj Tewari

In this paper we introduce a novel way of estimating prediction uncertainty in deep networks through the use of uncertainty surrogates. These surrogates are features of the penultimate layer of a deep network that are forced to match…

Machine Learning · Computer Science 2021-04-19 Radhakrishna Achanta , Natasa Tagasovska

In this paper, we address the critical need for interpretable and uncertainty-aware machine learning models in the context of online learning for high-risk industries, particularly cyber-security. While deep learning and other complex…

Machine Learning · Computer Science 2024-11-15 Benjamin Kolicic , Alberto Caron , Chris Hicks , Vasilios Mavroudis

Bridging continuous perceptual signals and discrete symbolic reasoning is a fundamental challenge in AI systems that must operate under uncertainty. We present a neuro-symbolic framework that explicitly models and propagates uncertainty…

Artificial Intelligence · Computer Science 2025-11-19 Jiahao Wu , Shengwen Yu

Most uncertainty-aware robotic systems collapse prediction uncertainty into a single scalar score and use it to trigger uniform corrective responses. This aggregation obscures whether uncertainty arises from corrupted observations or from…

The interdependence between nodes in graphs is key to improve class predictions on nodes and utilized in approaches like Label Propagation (LP) or in Graph Neural Networks (GNN). Nonetheless, uncertainty estimation for non-independent…

Machine Learning · Statistics 2021-10-28 Maximilian Stadler , Bertrand Charpentier , Simon Geisler , Daniel Zügner , Stephan Günnemann

When automated decision systems fail, organizations frequently discover that formally compliant governance infrastructure cannot reconstruct what happened or why. This paper synthesizes an operational governance evidence framework --…

Computers and Society · Computer Science 2026-04-27 Oleg Solozobov

Mechanistic interpretability aims to understand neural networks by identifying which learned features mediate specific behaviors. Attribution graphs reveal these feature pathways, but interpreting them requires extensive manual analysis --…

Computation and Language · Computer Science 2025-11-11 Giuseppe Birardi

Graph neural networks have demonstrated remarkable success in predicting molecular properties by leveraging the rich structural information encoded in molecular graphs. However, their black-box nature reduces interpretability, which limits…

Machine Learning · Computer Science 2025-08-22 Sebastian Musiał , Bartosz Zieliński , Tomasz Danel

We study aleatoric and epistemic uncertainty estimation in a learned regressive system dynamics model. Disentangling aleatoric uncertainty (the inherent randomness of the system) from epistemic uncertainty (the lack of data) is crucial for…

Machine Learning · Computer Science 2025-03-21 Zhiyu An , Zhibo Hou , Wan Du

In this work we introduce a manifold learning-based surrogate modeling framework for uncertainty quantification in high-dimensional stochastic systems. Our first goal is to perform data mining on the available simulation data to identify a…

Machine Learning · Statistics 2024-11-11 Dimitris G. Giovanis , Dimitrios Loukrezis , Ioannis G. Kevrekidis , Michael D. Shields

Probabilistic Circuits (PCs) are deep generative models that support exact and efficient probabilistic inference. Yet in autoregressive language modeling, PCs still lag behind Transformer-based large language models (LLMs), suggesting an…

Machine Learning · Computer Science 2026-05-14 Zhiyu Zhao , Xuejie Liu , Muhan Zhang , Anji Liu

Obtaining high certainty in predictive models is crucial for making informed and trustworthy decisions in many scientific and engineering domains. However, extensive experimentation required for model accuracy can be both costly and…

Machine Learning · Computer Science 2024-12-17 Giorgio Morales , John Sheppard

Modeling uncertainty in deep neural networks, despite recent important advances, is still an open problem. Bayesian neural networks are a powerful solution, where the prior over network weights is a design choice, often a normal…

Machine Learning · Statistics 2019-10-29 Raanan Y. Rohekar , Yaniv Gurwicz , Shami Nisimov , Gal Novik

Uncertainty is a key feature of any machine learning model and is particularly important in neural networks, which tend to be overconfident. This overconfidence is worrying under distribution shifts, where the model performance silently…

Machine Learning · Computer Science 2024-03-18 Arthur Thuy , Dries F. Benoit

There is a growing concern about typically opaque decision-making with high-performance machine learning algorithms. Providing an explanation of the reasoning process in domain-specific terms can be crucial for adoption in risk-sensitive…

Computer Vision and Pattern Recognition · Computer Science 2022-11-28 Aditya Chattopadhyay , Stewart Slocum , Benjamin D. Haeffele , Rene Vidal , Donald Geman

In modern engineering, physical processes are modelled and analysed using advanced computer simulations, such as finite element models. Furthermore, concepts of reliability analysis and robust design are becoming popular, hence, making…

Methodology · Statistics 2017-03-20 Roland Schöbi , Bruno Sudret

Reliable uncertainty estimates are crucial in modern machine learning. Deep Gaussian Processes (DGPs) and Deep Sigma Point Processes (DSPPs) extend GPs hierarchically, offering promising methods for uncertainty quantification grounded in…

Machine Learning · Statistics 2025-04-25 Matthijs van der Lende , Jeremias Lino Ferrao , Niclas Müller-Hof

We present a deep learning framework for probabilistic pixel-wise semantic segmentation, which we term Bayesian SegNet. Semantic segmentation is an important tool for visual scene understanding and a meaningful measure of uncertainty is…

Computer Vision and Pattern Recognition · Computer Science 2016-10-12 Alex Kendall , Vijay Badrinarayanan , Roberto Cipolla

The shape of an object is an important characteristic for many vision problems such as segmentation, detection and tracking. Being independent of appearance, it is possible to generalize to a large range of objects from only small amounts…

Machine Learning · Statistics 2018-12-14 Alessandro Di Martino , Erik Bodin , Carl Henrik Ek , Neill D. F. Campbell