paper-with-me

홈 › Papers

An Exploration And Validation of Visual Factors in Understanding Classification Rule Sets

2021-09-19 · Jun Yuan, Oded Nov, Enrico Bertini

Rule sets are often used in Machine Learning (ML) as a way to communicate the model logic in settings where transparency and intelligibility are necessary. Rule sets are typically presented as a text-based list of logical statements (rules). Surprisingly, to date there has been limited work on exploring visual alternatives for presenting rules. In this paper, we explore the idea of designing alternative representations of rules, focusing on a number of visual factors we believe have a positive impact on rule readability and understanding. We then presents a user study exploring their impact. The results show that some design factors have a strong impact on how efficiently readers can process the rules while having minimal impact on accuracy. This work can help practitioners employ more effective solutions when using rules as a communication strategy to understand ML models.

📄 PDF Abstract BibTeX arXiv:2109.09160

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Visualizing Rule Sets: Exploration and Validation of a Design Space

2021-03-01 · Jun Yuan, Oded Nov, Enrico Bertini

Rule sets are often used in Machine Learning (ML) as a way to communicate the model logic in settings where transparency and intelligibility are necessary. Rule sets are typically presented as a text-based list of logica…

Visualizing Linguistic Change as Dimension Interactions

2019-08-01 · WS 2019 8 · Christin Sch{\"a}tzle, Frederik L. Dennig, Michael Blumenschein, Daniel A. Keim 외

Historical change typically is the result of complex interactions between several linguistic factors. Identifying the relevant factors and understanding how they interact across the temporal dimension is the core remit o…

Towards Understanding the Robustness Against Evasion Attack on Categorical Data

2021-09-29 · ICLR 2022 4 · Hongyan Bao, Yufei Han, Yujun Zhou, Yun Shen 외

Characterizing and assessing the adversarial vulnerability of classification models with categorical input has been a practically important, while rarely explored research problem. Our work echoes the challenge by first …

Classification

Beyond Measurement Metrics: A Human-Centered Framework for Semantic Validation of Network Traffic Classification

2026-09-15 · Igor Cherepanov, David Sessler, Alex Ulmer, Thorsten May 외 arxiv

Machine learning (ML) has become the dominant approach for network traffic classification, achieving very high predictive performance. However, a model is only valuable if it learns semantically meaningful and trustworth…

YOLO -- You only look 10647 times

2022-01-16 · Christian Limberg, Andrew Melnik, Augustin Harter, Helge Ritter

With this work we are explaining the "You Only Look Once" (YOLO) single-stage object detection approach as a parallel classification of 10647 fixed region proposals. We support this view by showing that each of YOLOs out…

Classificationimage-classificationImage ClassificationObject+3