Deploying ML models to the real world is prone to uncover domain coverage issues. Let’s robustify the models by generating unseen data!

In the first year of my PhD, I started trauma recovery therapy to heal from domestic violence. It mostly consisted of something called “reprocessing sessions”; using a technique called EMDR we would revisit traumatic memories in my life, and try to figur…

Image generation with VQGAN + CLIP Colab by Katherine Crowson & Tutorial by Sam King…

Interpretability in machine learning (ML) is crucial for high stakes decisions and troubleshooting. In this work, we provide fundamental principles for interpretable ML, and dispel common misunderstandings that dilute the importance of this crucial topic….

There has always been a census undercount because some people are hard to locate, contact, and interview. Read here how OmniSci is used to visualize a massive GPS mobility dataset, correlate the observations with historical censuses, and then predict cens…

This summer I’ve been competing in the SLICED machine learning competition, where contestants have two hours to open a new dataset, build a predictive model, and be scored as a Kaggle submission. Contestants are graded primarily on model performance, but …

Berkeley-based project could support action worldwide on climate, health and poverty…

Interview with Vicki Boykis on applying machine learning at work…

This article is a high-level introduction to an efficient worfklow for optimizing runtime performance of machine learning systems running on the GPU. Using traces from Nsight Systems to show real production scenarios, I introduce a set of common utilizati…