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.
More from Companies & People
- Google's $20 Workspace AI add-on slammed for leaving enterprise Gemini stuck on old Flash model — thedealdirector · 2026-09-25
- Elicit hosts Merck KGaA's Parantu Shah on scaling AI in biopharma, Oct 7 — elicitorg · 2026-09-25
- Lambda's Stephen Balaban on 14 years, 5 pivots, and debunking data center myths — gharik · 2026-09-25
- Nadella echoes bet that AI race is shifting from models to products with new Copilot — satyanadella · 2026-09-25
- MIT mocks Harvard's A-grade cap: critics say it will push students to ChatGPT their way to a 4.0 — jonippolito · 2026-09-25
- Australia to host large share of next-gen datacenters, built for Anthropic — mattbeane · 2026-09-25