I’m still kind of getting situated here and figuring out how I’m going to work. I’m working on building a new website, Bottom-Up Labs, that’s dedicated to my exploration of various AI topics. Yesterday, I posted Einops basics there.

Today (11/05) I completed What is torch.nn really?, which is an introduction to PyTorch’s neural network modules, classes, etc. Embarrassing to admit, but I haven’t really worked much with it before, just some tinkering. It was really neat to see how simply models can be trained, modified, etc, especially with switching from a simple neural network to a convolutional neural network.

I’m also working through the first notebook of a series I’m working on about interpretability, using NES games: Meet Mario. It’s not finished, and I ran out of time today, but it’s coming!