Professor's AI-built neural network explainers are transforming his deep learning classroom

davidbau · x · 2026-09-25

Northeastern's David Bau released interactive deep learning explainers for CS7150, built with Claude and Codex, covering perceptrons, optimizers (full Adam derivation), initialization (Glorot & Bengio 2010), linear algebra and probability — all browser-based with Colab notebooks.

He observes the AI age is changing his classroom: students finish even 1-point homework, request more tests, talk more, and are more willing to say "I don't get it."

Resources: cs7150.github.io and github.com/CS7150/classdemos, including a 20-round transcript of using an AI agent to learn the perceptron algorithm.

Original post →

More from Companies & People

Companies & People channel →