Back to Topic 4.3 — Machine learning approaches
4.3.9Computer Science HL5 flashcards

CNNs

Practice Flashcards

Flip to reveal answers
Card 1 of 54.3.9
4.3.9
Question

What does convolution do in a CNN?

Click to reveal answer

Track your progress — Sign up free to save your progress and get smart review reminders based on spaced repetition.

All 5 Flashcards — CNNs

Sign up free to track progress and get spaced-repetition review schedules.

Card 1process

Question

What does convolution do in a CNN?

Answer

Slides a small **filter** of weights across the input, multiplying and summing at each position to produce a **feature map** of where that pattern occurs.

Card 2concept

Question

Why are shared weights important?

Answer

The **same** filter is used at every position, so a feature is recognised **wherever it appears** — and one detector costs a handful of weights rather than a set per location.

Card 3definition

Question

What is pooling for?

Answer

Keeping the strongest value in each block: **fewer numbers** to carry forward, and tolerance to small shifts in position.

Card 4concept

Question

What do successive CNN layers learn?

Answer

**Edges**, then shapes built from edges, then objects built from shapes — a hierarchy that is learned rather than designed.

Card 5concept

Question

Why is flattening an image a problem?

Answer

It **destroys the geometry** — the network no longer knows which pixels were adjacent — and a 200×200 colour image gives 120,000 inputs, needing millions of weights.

Track your progress with spaced repetition

Sign up free — Aimnova tells you exactly which cards to review and when, so you remember everything before your IB exam.

Start Free
IB Computer Science CNNs Flashcards | 4.3.9 | Aimnova