paper-with-me

홈 › Papers

Conceptualizing Uncertainty

2025-03-05 · Isaac Roberts, Alexander Schulz, Sarah Schroeder, Fabian Hinder, Barbara Hammer

Uncertainty in machine learning refers to the degree of confidence or lack thereof in a model's predictions. While uncertainty quantification methods exist, explanations of uncertainty, especially in high-dimensional settings, remain an open challenge. Existing work focuses on feature attribution approaches which are restricted to local explanations. Understanding uncertainty, its origins, and characteristics on a global scale is crucial for enhancing interpretability and trust in a model's predictions. In this work, we propose to explain the uncertainty in high-dimensional data classification settings by means of concept activation vectors which give rise to local and global explanations of uncertainty. We demonstrate the utility of the generated explanations by leveraging them to refine and improve our model.

📄 PDF Abstract BibTeX arXiv:2503.03443

Code (1)

robertsi20/Conceptualizing-Uncertainty 공식 구현 pytorch

Tasks

Uncertainty Quantification

Similar Papers 제목 키워드 기반

Conceptualizing EDUCATION in Hong Kong and China (1984-2014)

2017-11-01 · PACLIC 2017 11 · Kathleen Ahrens, Huiheng Zeng

Credal Transformer: A Principled Approach for Quantifying and Mitigating Hallucinations in Large Language Models

2025-10-14 · Shihao Ji, Zihui Song, Jiajie Huang arxiv

Large Language Models (LLMs) hallucinate, generating factually incorrect yet confident assertions. We argue this stems from the Transformer's Softmax function, which creates "Artificial Certainty" by collapsing ambiguous…

ExACT: Language-guided Conceptual Reasoning and Uncertainty Estimation for Event-based Action Recognition and More

2024-03-19 · CVPR 2024 1 · Jiazhou Zhou, Xu Zheng, Yuanhuiyi Lyu, Lin Wang

Event cameras have recently been shown beneficial for practical vision tasks, such as action recognition, thanks to their high temporal resolution, power efficiency, and reduced privacy concerns. However, current researc…

Action Recognition

Language Models as Semiotic Machines: Reconceptualizing AI Language Systems through Structuralist and Post-Structuralist Theories of Language

2024-10-16 · Elad Vromen

This paper proposes a novel framework for understanding large language models (LLMs) by reconceptualizing them as semiotic machines rather than as imitations of human cognition. Drawing from structuralist and post-struct…

A Bayesian Analysis of Dynamics in Free Recall

2009-12-01 · NeurIPS 2009 12 · Richard Socher, Samuel Gershman, Per Sederberg, Kenneth Norman 외

We develop a probabilistic model of human memory performance in free recall experiments. In these experiments, a subject first studies a list of words and then tries to recall them. To model these data, we draw on both …

Bayesian InferenceRetrievalTopic Models