🎙 Free live masterclass · Sun, 29 Nov, 7:00 pm IST · Java Full Stack roadmap Register free →
Skills101
← 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 →
  1. Q1. Why can logistic regression not learn XOR?
  2. Q2. What does a single neuron compute?
  3. Q3. What does this print? (code)
  4. Q4. A network has 5 layers but no activation functions. How powerful is it?
  5. Q5. In the hand-built XOR network, which two rules do the hidden neurons compute?
  6. Q6. What does backpropagation compute?
  7. Q7. What does this print? (code)
  8. Q8. Why should you not start all weights at zero?
  9. Q9. Which activation is the usual default for hidden layers in large modern networks?
  10. Q10. The XOR network trained with seed 2 got stuck with predictions of 0.5 on two cases. What is a sensible fix?