Lab 11 · Quiz
Neural Networks Quiz
Neurons & activations
Multilayer perceptrons
Gradient descent
Back-propagation
Work in progress This quiz is still being reviewed: questions may change, and some parts may still contain mistakes.
Before you start
Quiz for Lab 11: Neural Networks. Answer every task, then press Check answers at the bottom: each answer is marked, the explanations appear, and you get a score per skill.
Assumptions unless stated otherwise
- A neuron computes a weighted sum plus bias, then applies an activation: \(a = g\big(\sum_j w_j x_j + b\big)\).
- Feed-forward networks have no cycles; hidden layers lie between the input and output layers.
- Gradient descent moves the parameters in the direction that reduces the cost; lower training loss means a better fit to the training set.
How answers are scored
- Numbers: type the value as a decimal, e.g. 0.73; large numbers may use separators (314,000).
- Select all that apply: scores only when the selection is exactly right.
- Rows: one choice per row; each correct row earns its share of the points.
- Your answers are saved in this browser only, so you can leave and come back. Nothing is sent anywhere.