Hierarchical Structure of Uncertainty
We introduce a new concept called uncertainty spaces which is an extended concept of probability spaces. Then, we express n-layer uncertainty which we call hierarchical uncertainty by a hierarchically constructed sequence of uncertainty spaces, called a U-sequence. We use U-sequences for providing examples that illustrate Ellsberg's paradox. We will use the category theory to get a bird's eye view of the hierarchical structure of uncertainty. We discuss maps between uncertainty spaces and maps between U-sequences, seeing that they form categories of uncertainty spaces and the category of U-sequences, respectively. We construct an endofunctor of the category of measurable spaces in order to embed a given U-sequence into it. Then, by the iterative application of the endofunctor, we construct the universal uncertainty space which may be able to serve as a basis for multi-layer uncertainty theory.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Hierarchical brain parcellation with uncertainty
Many atlases used for brain parcellation are hierarchically organised, progressively dividing the brain into smaller sub-regions. However, state-of-the-art parcellation methods tend to ignore this structure and treat lab…
LLM-Guided Taxonomy and Hierarchical Uncertainty for 3D Point CLoud Active Learning
We present a novel active learning framework for 3D point cloud semantic segmentation that, for the first time, integrates large language models (LLMs) to construct hierarchical label structures and guide uncertainty-bas…
Active LearningSemantic SegmentationElongated Physiological Structure Segmentation via Spatial and Scale Uncertainty-aware Network
Robust and accurate segmentation for elongated physiological structures is challenging, especially in the ambiguous region, such as the corneal endothelium microscope image with uneven illumination or the fundus image wi…
Retinal Vessel SegmentationSegmentationHierarchical Selective Classification
Deploying deep neural networks for risk-sensitive tasks necessitates an uncertainty estimation mechanism. This paper introduces hierarchical selective classification, extending selective classification to a hierarchical …
ClassificationKnowledge DistillationSpecificityHierarchical Reinforcement Learning Framework for Stochastic Spaceflight Campaign Design
This paper develops a hierarchical reinforcement learning architecture for multimission spaceflight campaign design under uncertainty, including vehicle design, infrastructure deployment planning, and space transportatio…
Hierarchical Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+1