Machine learning
Loss function first. Model second.
the shape of this subject
ML has a copy-paste culture that hides misunderstanding. Brainback keeps you defining the loss and the evaluation metric before you tune a hyperparameter.
Because machine learning rewards the students who do the reps — and punishes the ones who outsource them.
- discipline
- STEM
- parent subject
- Computer science
- typical weekly load
- 3-6 problem sets · 3-5 hours · 1-2 recall sessions
- covered on plan
- all plans (free forever)
Every machine learning concept Brainback covers.
Add Machine learning as a Learn subject and every problem in these areas routes to the Socratic tutor — attempt-first, hint-laddered, output-guarded.
What one turn in machine learning actually looks like.
Attempt → correction → guiding question. No answer. Ever. Verbatim from a beta session.
Logistic regression with L2 penalty; step size 0.01…
What loss are you minimizing? What does its gradient tell you?
no answer · one guiding question · your next move
How real attempts start. How Brainback nudges.
- Logistic regression with L2 penalty; step size 0.01…
- What loss are you minimizing? What does its gradient tell you?
the anti-pattern
What machine learning looks like when the AI does the thinking.
Answer machines make machine learning look like a solved problem. It isn't. The exam room reveals whose reasoning was built and whose was rented.
- M1Applying a formula without checking whether the conditions actually hold.
- M2Skipping the sanity check — 'does the sign / magnitude make sense?'
- M3Memorizing steps instead of reasoning about why they're legal.
- M4Reading past the setup and diving straight into computation.
the recall card
What a spaced-repetition card looks like in machine learning.
Every wrong attempt and low-scored explain-back becomes a card. SM-2 schedules them — the tricky ones come back tomorrow, the solid ones drift out to next week, then next month.
Recall the core concept in your own words. Then apply it to a fresh example under 2 minutes.
Related subjects.
The subject where the shortcut has always been most expensive.
Limits, rates, and shapes of change — earned, not delivered.
Where symbolic manipulation becomes second nature — or doesn't.
See the diagram. Not just look at it.
Unit circle, but also unit intuition.
Vectors are directions, not numbers.
machine learning — ready when you are
Start your first machine learning session.
Attempt-first. Never the answer. Add it as a Learn subject in 30 seconds.