Hi, I'm Fred Hohman

I’m a PhD candidate in the College of Computing at Georgia Tech.

I research how to enable machine learning interpretability at scale and for everyone, by designing and developing interactive interfaces to help people confidently understand data-driven systems. Besides building tools, I also create data visualizations and write interactive articles to simply communicate complex ideas.

At Georgia Tech I work with Polo Chau and Alex Endert as a member of the Polo Club of Data Science.

I have collaborated with designers, developers, and scientists while working at

Apple,

Microsoft Research,

NASA Jet Propulsion Lab, and

Pacific Northwest National Lab.

My research is supported by a NASA Space Technology Research Fellowship.

Featured Research Publications

Chameleon

Understanding and visualizing data iteration in machine learning

CHI 2020

Summit

Scaling deep learning interpretability by visualizing activation and attribution summarizations

TVCG 2020

Gamut

A design probe to understand how data scientists understand machine learning models

CHI 2019

Visual Analytics in Deep Learning

An interrogative survey

TVCG 2018

Featured Interactive Articles

Parametric Press

A born-digital magazine showcasing the expository power of the web

Present —

The Myth of the Impartial Machine

Can we free machine learning models from bias and prejudice?

May 2019

Dimensionality Reduction

Explore the methods data scientists use to visualize high-dimensional data

July 2018

The Math of Card Shuffling

Riffling from factory order to complete randomness

June 2018

Everything Else