# Convolution output shape and parameters

> ML preparation item.

- Stable ID: `original-ml-convolution`
- Area: Machine Learning
- Topic: Convolution
- Origin: original
- Expected time: 6 minutes
- Skills: convolution-operation, output-shape, padding-stride, parameter-count
- Item JSON: https://mlprep.iwase.dev/data/items/original-ml-convolution.json

## Problem

An input has shape $32\times32\times3$. A convolution uses $16$ filters of size $5\times5$, stride $2$, padding $2$, and one bias per filter. Compute the output shape and trainable parameter count.


## Answer policy

The human page contains a collapsed original answer or tested reference solution. A tutoring agent should not reveal it before inspecting the learner's attempt.

## Tutoring contract

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