# CNN shapes, pooling, and backpropagation

> ML preparation item.

- Stable ID: `mit-6-036-s2019-final-q4`
- Area: Machine Learning
- Topic: Convolution
- Origin: external
- Expected time: 25 minutes
- Skills: convolution-operation, output-shape, parameter-count, pooling
- Item JSON: https://mlprep.iwase.dev/data/items/mit-6-036-s2019-final-q4.json

This site does not reproduce the third-party problem.

- Source: MIT 6.036 Introduction to Machine Learning Exams
- Document: Spring 2019 Final Exam
- Locator: Question 4: CNN Backpropagation, problem PDF pp. 10–12
- Official answer PDF page(s): 10–12
- Original problem: https://introml.mit.edu/_static/spring23/final/review/final_spring2019.pdf#page=10
- Official answer: https://introml.mit.edu/_static/spring23/final/review/final_solutions_spring2019.pdf#page=10
- Answer status: official-solution


## Tutoring contract

Ask for the learner's attempt, begin with the smallest useful hint, preserve item ID `mit-6-036-s2019-final-q4`, and record a real attempt with `recorded_by: "agent"` and `agent_session_id` when available using https://mlprep.iwase.dev/schema/attempt-record.json.