AI & Machine Learning Forward Pass & Loss Functions Quiz

This quiz follows a batch of data through a neural network layer and into the loss. You will work out shapes and parameter counts, compute softmax and cross-entropy with small numbers and choose the right loss for the task.

Medium 10 questions ~6 minutes Pass at 80%

Choose a mode

Playing as a guest: sign in to keep your XP and streak.

Sample question

Question 1 of 10

A dense layer takes 4 inputs and has 3 neurons. How many trainable parameters does it have?

Show the answer

C. 15 Each of the 3 neurons has 4 weights and 1 bias: 4 * 3 + 3 = 15. 12 forgets the biases.

What this quiz covers

  • Shapes in a dense layer X @ W + b
  • Counting weights and biases
  • Softmax, logits and numerical stability
  • Cross-entropy and binary cross-entropy by hand
  • Averaging the loss over a batch

Questions people ask

Do I need an account?

No. Anyone can play. Sign in to keep your XP, streak, badges and history.

Can I retake it?

Yes. Your best score is kept, and the questions and answers are shuffled each time.