Practice Flashcards
Flip to reveal answersWhat does one unit in a neural network compute?
Track your progress — Sign up free to save your progress and get smart review reminders based on spaced repetition.
All 5 Flashcards — Neural networks
Sign up free to track progress and get spaced-repetition review schedules.
Question
What does one unit in a neural network compute?
Answer
Each input **times a weight**, summed, **plus a bias**, passed through an **activation function**.
Question
Name the three kinds of layer.
Answer
**Input** (one unit per feature), **hidden** (where the work happens), **output** (one unit per class).
Question
Why is a non-linear activation essential?
Answer
Without it, stacked layers collapse into a **single weighted sum** — a hundred layers would have the power of one.
Question
What is backpropagation?
Answer
Working **backwards** from the error to find each weight's contribution, so every weight can be nudged in the direction that reduces it.
Question
What does training change, and what does it not?
Answer
It changes the **weights and biases**. The number of layers, units and the activation function are **hyperparameters**, fixed beforehand.
Read the notes
Full study notes for Neural networks
Topic 4.3 hub
Machine learning approaches
More from Topic 4.3
All flashcards in this topic
Computer Science exam skills
Paper structures & tips
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