AI & Machine Learning Neurons & Activation Functions Quiz

This beginner-friendly deep learning quiz starts with a single artificial neuron. It checks that you can compute a neuron's output and know when to use ReLU, sigmoid, tanh or softmax.

Easy 10 questions ~5 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

What does a single artificial neuron compute?

Show the answer

B. A weighted sum of its inputs plus a bias, passed through an activation function A neuron computes z = w1*x1 + ... + wn*xn + b, then applies an activation such as ReLU to z. The weights and bias are what training learns.

What this quiz covers

  • A neuron as weighted sum + bias + activation
  • ReLU, sigmoid and tanh and their output ranges
  • Why networks need non-linear activations
  • Softmax and sigmoid output layers
  • The dying ReLU problem and Leaky ReLU

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.