Neal Jean

I'm a PhD student working with Stefano Ermon in the Stanford AI Lab, where we're using machine learning to tackle challenging problems in sustainability and healthcare. I've also spent some time at the Future of Humanity Institute at the University of Oxford.

I previously studied econ and math at Duke and electrical engineering at Georgia Tech. I love basketball — my senior thesis was about the NBA — but unfortunately I'm too deep in this school thing now to make it to the league.

Email  /  Twitter  /  Scholar  /  GitHub  /  LinkedIn


I'm currently interested in deep generative models, semi-supervised learning, weak supervision, and applications in computational sustainability and healthcare.

Combining satellite imagery and machine learning to predict poverty
Neal Jean, Marshall Burke, Michael Xie, W. Matthew Davis, David B. Lobell, Stefano Ermon
Science, 353(6301), 790-794, 2016  
Video / PDF / Website / Commentary / Code

Produced district-level poverty maps in Nigeria, Tanzania, Uganda, Malawi, and Rwanda based on household consumption and asset-based wealth measures. Bill Gates tweeted our research!

Transfer learning from deep features for remote sensing and poverty mapping
Michael Xie, Neal Jean, Marshall Burke, David B. Lobell, Stefano Ermon
AAAI Conference on Artificial Intelligence, 2016  
PDF / NY Times

Extracted features from high-resolution satellite images with convolutional neural networks to estimate poverty in Uganda.

Workshop submissions

Enabling Rapid Screening of Bacterial Blood Infections with Machine Learning
Neal Jean, Chi-Sing Ho, Amr Saleh, Niaz Banaei, Jennifer Dionne, Stefano Ermon
ICML Workshop in Computational Biology, 2017  

Using single-cell Raman spectra to classify bacterial blood infections — the eventual goal is to do point-of-care diagnosis in a matter of hours.

Semi-supervised deep kernel learning
Neal Jean, Michael Xie, Stefano Ermon
NIPS Bayesian Deep Learning Workshop, 2016  
PDF / Poster

Adapted Deep Kernel Learning models for semi-supervised learning.