AI by Hand ✍️

AI by Hand ✍️

Linear Probe

Fine-Tuning series: 5 of 8

Prof. Tom Yeh's avatar
Prof. Tom Yeh
Apr 24, 2026
∙ Paid

Library › Fine-Tuning

  1. Weight Update

  2. Pretrain vs Fine-Tune

  3. Full Fine-Tuning

  4. Freezing Layers

  5. Linear Probe

  6. Feature Extraction + Head

  7. Adapter Layers

  8. LoRA

In Freezing Layers, we kept the foundational prerequisites fixed and refreshed only the advanced course on top, W₃. But even refreshing one course is still a whole course. W₃ is a full 40 × 40 matrix (1600 weights to update), weeks of lectures, assignments, and exams to work through. What if we don't re-take any existing course at all, and instead pick up a single new one-credit certificate, the kind you can finish in a month?

Paid members: the full breakdown continues below ↓

This post is for paid subscribers

Already a paid subscriber? Sign in
© 2026 Tom Yeh · Privacy ∙ Terms ∙ Collection notice
Start your SubstackGet the app
Substack is the home for great culture