- The ConvMixer architecture: 🤷 (December 2021)
- I am training a deep network on a GPU using the Flux.jl library. There are two takeaway messages: 1) patches are all you need, 2) in Julia, the ConvMixer *largely* fits in one Tweet.
- The double descent phenomenon (November 2021)
- Why do overparametrized networks do well?
- An inverse visualization for the elliptic law (March 2021)
- A beautiful colorplot of the characteristic polynomial of random matrices.
- The dimension of invariant and equivariant linear layers (July 2021)
- We compute the dimension of equivariant linear layers in neural architectures.
- Waves on donuts (August 2021)
- A nice plot of random Laplace eigenfuctions on the torus, also called random arithmetic waves.
- Random line processes (August 2021)
- How to draw random lines on the plane.
- Random analytic functions: Ryll-Nardzewski's theorem (April 2021)
- What happens at the boundary of the disk of convergence of random analytic series.
More to come.