Daniel Kerrigan
Research
I am interested in visualization and HCI, particularly as they relate to the development, evaluation, and use of machine learning models.
In progress
SAEfarer
SAEfarer is a visual analytics tool for exploring sparse autoencoders, with a particular focus on labeled data.
Monomoy
Monomoy is a system for helping domain experts familiarize themselves with and identify unintuitive behavior in machine learning models.
Published
PDPilot: Exploring Partial Dependence Plots Through Ranking, Filtering, and Clustering
Daniel Kerrigan, Brian Barr, and Enrico Bertini
IEEE Transactions on Visualization and Computer Graphics, 2025
Towards a Visual Perception-Based Analysis of Clustering Quality Metrics
Graziano Blasilli, Daniel Kerrigan, Enrico Bertini, Giuseppe Santucci
Visualization in Data Science (VDS at IEEE VIS), 2024
Measuring wake deflection from SCADA data during wake steering using machine learning
Nathan Post, Cheng Zheng, Daniel Kerrigan, Enrico Bertini, Melanie Tory
Journal of Physics: Conference Series, 2024
SliceLens: Guided Exploration of Machine Learning Datasets
Daniel Kerrigan, Enrico Bertini
In Proceedings of the Workshop on Human-In-the-Loop Data Analytics (HILDA '23), 2023
A Survey of Domain Knowledge Elicitation in Applied Machine Learning
Daniel Kerrigan, Jessica Hullman, Enrico Bertini
Multimodal Technologies and Interaction, 2021
Nutrition Bytes: Visualizing Food Content
Shuai He, Daniel Kerrigan, Ronald Metoyer
IEEE VIS Poster Extended Abstract, 2017