research
∙
06/16/2021
Best of both worlds: local and global explanations with human-understandable concepts
Interpretability techniques aim to provide the rationale behind a model'...
share
research
∙
08/12/2020
The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models
We present the Language Interpretability Tool (LIT), an open-source plat...
research
∙
07/14/2019
The Bach Doodle: Approachable music composition with machine learning at scale
To make music composition more approachable, we designed the first AI-po...
research
∙
07/09/2019
The What-If Tool: Interactive Probing of Machine Learning Models
A key challenge in developing and deploying Machine Learning (ML) system...
research
∙
02/07/2019
Automating Interpretability: Discovering and Testing Visual Concepts Learned by Neural Networks
Interpretability has become an important topic of research as more machi...
research
∙
10/13/2018
ClinicalVis: Supporting Clinical Task-Focused Design Evaluation
Making decisions about what clinical tasks to prepare for is multi-facto...
research
∙
01/24/2018