Strong & Weak Methods: A Logical View of Uncertainty
The last few years has seen a growing debate about techniques for managing uncertainty in AI systems. Unfortunately this debate has been cast as a rivalry between AI methods and classical probability based ones. Three arguments for extending the probability framework of uncertainty are presented, none of which imply a challenge to classical methods. These are (1) explicit representation of several types of uncertainty, specifically possibility and plausibility, as well as probability, (2) the use of weak methods for uncertainty management in problems which are poorly defined, and (3) symbolic representation of different uncertainty calculi and methods for choosing between them.
Code (0)
등록된 구현이 없습니다.
Tasks
ManagementSimilar Papers 제목 키워드 기반
Modeling the Ellsberg Paradox by Argument Strength
We present a formal measure of argument strength, which combines the ideas that conclusions of strong arguments are (i) highly probable and (ii) their uncertainty is relatively precise. Likewise, arguments are weak when …
Unbalanced Incomplete Multi-view Clustering via the Scheme of View Evolution: Weak Views are Meat; Strong Views do Eat
Incomplete multi-view clustering is an important technique to deal with real-world incomplete multi-view data. Previous works assume that all views have the same incompleteness, i.e., balanced incompleteness. However, di…
ClusteringIncomplete multi-view clusteringMulti-view Subspace ClusteringEvaluating Risks in Weak-to-Strong Alignment: A Bias-Variance Perspective
Weak-to-strong alignment offers a promising route to scalable supervision, but it can fail when a strong model becomes confidently wrong on examples that lie in the weak model's blind spots. Understanding such failures r…
Reinforcement LearningGive me (un)certainty -- An exploration of parameters that affect segmentation uncertainty
Segmentation tasks in medical imaging are inherently ambiguous: the boundary of a target structure is oftentimes unclear due to image quality and biological factors. As such, predicted segmentations from deep learning al…
SegmentationUncertainty QuantificationHarnessing Weak Pair Uncertainty for Text-based Person Search
In this paper, we study the text-based person search, which is to retrieve the person of interest via natural language description. Prevailing methods usually focus on the strict one-to-one correspondence pair matching b…
Contrastive LearningImage-text matchingPerson Search