← All topics
Quiz: Neural Networks from Scratch: questions with answers
10 questions, each with the answer and a short explanation.
Take the timed quiz + get a certificate →- Q1. Why can logistic regression not learn XOR?
- Q2. What does a single neuron compute?
- Q3. What does this print? (code)
- Q4. A network has 5 layers but no activation functions. How powerful is it?
- Q5. In the hand-built XOR network, which two rules do the hidden neurons compute?
- Q6. What does backpropagation compute?
- Q7. What does this print? (code)
- Q8. Why should you not start all weights at zero?
- Q9. Which activation is the usual default for hidden layers in large modern networks?
- Q10. The XOR network trained with seed 2 got stuck with predictions of 0.5 on two cases. What is a sensible fix?