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.
Current project
Can we make it more fun to explore the space of new AI models? Could exploring Deep Learning architectures and training regimes become more fun than playing Minecraft?
So far, two ML libraries have spun out from this project:
- Vexpr: use Lisp-like code transformation to make models readable, fast, and visualizable
- rows2prose: visualize models by rendering scalars into styled text
Blog
Expressions are Pragmatic Model Visualizations
2024-01-10
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
Poster at 30th Annual Computational Neuroscience Meeting (2021)
PLOS Computational Biology (2020)
Front. Neural Circuits (2019)
Front. Neural Circuits (2019)