I am a programmer and researcher who wants to make computers more fun and empowering for students, researchers, and engineers. I thought the field was stuck, so I moved from computer science to neuroscience in search of ideas for making computers smarter. Then, to my surprise, the computers went and got smarter. Now, with all this low-hanging fruit around, I'm back to focusing directly on computers.

Here is my angle. Rather than focusing primarily on making things "easy", I think computers should encourage people to take ownership of all the complexity of whatever they are doing. Tools should be built for experts, with good on-ramps for everybody else. I am excited about LLMs and how they can make tools for experts more approachable for everyone.

Current project

Building Vexpr, a new Python library that embraces Lisp-like code transformation to make code readable, fast, and visualizable.

Building user interfaces that make people better at using machine learning models.

Recent blog posts

What happens when you vectorize wide PyTorch expressions?
2023-10-19

Gaussian Processes Extrapolate, Sometimes in Goofy Ways
2023-03-28

Maybe Bayesian Optimization Should Be Harder, Not Easier
2022-11-30

Imagine A Deep Network That Performs Successive Cheap Queries On Its Input
2022-07-08

Bayesian Optimization Is More Basis-Dependent Than You Might Think
2022-06-26

Likely ≠ Typical: A Viewpoint On Why We Perturb Neural Networks
2022-01-28

Some "Causal Inference" intuition
2021-11-04

Select talks / presentations

Intro to Grid Cells + Quickly Forming Structured Memories
2021-06-07

Testing a possible explanation for grid cell distortions
2021-05-17

Journal Club: Hinton's GLOM + Numenta's TBT (after a year without a haircut)
2021-03-24

Using grid cells as a prediction-enabling basis
2020-12-22

The Minimum Description Length Principle, sparsity, and quantization
2020-04-01

Photo

(Photo credit: Rosanne Liu, 2023)

Papers

More

Older posts | Google Scholar | LinkedIn | Mastodon