Lesson 1: Sequence models: reading words in order
54 min read·14 Oct 2026
Module 7 · Lesson 1 · About 40 minutes · Needs: basic Python; Module 4 (TF-IDF and logistic regression) helps; no PyTorch needed
The situation
It is Monday 19 October 2026, project week 7. Rosa has heard that "deep learning" beats word counts and wants proof before paying for GPU time. Every model so far treats a message as a bag of words: it knows which words appear, not in what order.
One message runs through the lesson: HT08 from the hand-written test set (simulated). It reads "I don't want the Volt 2, I want something without a battery for my commute. Is the Harbour any good on hills?" Ines labels it product_question. Module 4's TF-IDF model sends it to Dev's warranty queue.