micromlp: A From-Scratch Neural Net That Predicts Housing Prices

Developer soasme released micromlp, a single-file Python neural network with no dependencies that predicts California housing prices using a 2-layer MLP and from-scratch automatic differentiation, inspired by Karpathy's microgpt. The project aims to close the gap between using PyTorch's .backward() and understanding backpropagation by hand.

I built micromlp https://gist.github.com/soasme/913a4ab4c554d7874695450d5cd56e97 : a single file of Python, no dependencies, no PyTorch. It downloads a real dataset, builds a 2-layer MLP, implements automatic differentiation from scratch, trains with gradient descent, and makes predictions. The task: the California housing dataset from chapter 2 of Hands-On Machine Learning https://www.oreilly.com/library/view/hands-on-machine-learning/9781098125967/ — predict a district’s median house value from its census stats. This is inspired by Karpathy’s microgpt https://karpathy.github.io/2026/02/12/microgpt/ . I’ve used PyTorch for years. I’d never actually written backprop by hand. There’s a difference between knowing .backward exists and knowing what it does when you call it — I found it worth closing that gap once, on a toy, instead of taking it on faith forever.