activity
20202023
most citedRECAST: Enabling User Recourse and Interpretability of Toxicity Detection Models with Interactive Visualization

31 citations · 70 across the 13 of their papers we have counts for

collaborators
Showing 2022Show all

2 papers · 1 filter

cs.HC2022

NeuroMapper: In-browser Visualizer for Neural Network Training

Zhiyan Zhou, Kevin Li, Haekyu Park +4

We present our ongoing work NeuroMapper, an in-browser visualization tool that helps machine learning (ML) developers interpret the evolution of a model during training, providing…

cs.LG2022

Concept Evolution in Deep Learning Training: A Unified Interpretation Framework and Discoveries

Haekyu Park, Seongmin Lee, Benjamin Hoover +7

We present ConceptEvo, a unified interpretation framework for deep neural networks (DNNs) that reveals the inception and evolution of learned concepts during training. Our work add…