paper-with-me

Papers

Interactive slice visualization for exploring machine learning models

2021-01-18 · Catherine B. Hurley, Mark O'Connell, Katarina Domijan

Machine learning models fit complex algorithms to arbitrarily large datasets. These algorithms are well-known to be high on performance and low on interpretability. We use interactive visualization of slices of predictor space to address the interpretability deficit; in effect opening up the black-box of machine learning algorithms, for the purpose of interrogating, explaining, validating and comparing model fits. Slices are specified directly through interaction, or using various touring algorithms designed to visit high-occupancy sections or regions where the model fits have interesting properties. The methods presented here are implemented in the R package \pkg{condvis2}.

📄 PDF Abstract BibTeX arXiv:2101.06986

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine Learning

Similar Papers 제목 키워드 기반

Quantum Machine Learning Playground

2025-07-23 · Pascal Debus, Sebastian Issel, Kilian Tscharke arxiv

This article introduces an innovative interactive visualization tool designed to demystify quantum machine learning (QML) algorithms. Our work is inspired by the success of classical machine learning visualization tools,…

Quantum Machine Learning

Visual Auditor: Interactive Visualization for Detection and Summarization of Model Biases

2022-06-25 · David Munechika, Zijie J. Wang, Jack Reidy, Josh Rubin 외

As machine learning (ML) systems become increasingly widespread, it is necessary to audit these systems for biases prior to their deployment. Recent research has developed algorithms for effectively identifying intersect…

InsightBoard: An Interactive Multi-Metric Visualization and Fairness Analysis Plugin for TensorBoard

2026-04-02 · Ray Zeyao Chen, Christan Grant arxiv

Modern machine learning systems deployed in safety-critical domains require visibility not only into aggregate performance but also into how training dynamics affect subgroup fairness over time. Existing training dashboa…

The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizations

2022-12-22 · A. Chatzimparmpas, R. Martins, I. Jusufi, K. Kucher 외

Machine learning (ML) models are nowadays used in complex applications in various domains, such as medicine, bioinformatics, and other sciences. Due to their black box nature, however, it may sometimes be hard to underst…

Who Defines "Best"? Towards Interactive, User-Defined Evaluation of LLM Leaderboards

2026-04-23 · Minji Jung, Minjae Lee, Yejin Kim, Sarang Choi 외 arxiv

LLM leaderboards are widely used to compare models and guide deployment decisions. However, leaderboard rankings are shaped by evaluation priorities set by benchmark designers, rather than by the diverse goals and constr…