Skills101
← All practice quizzes

Quiz: Neural Networks from Scratch

5 questions · new set on every retakeNo time limitPass: 60%+10 XP on first pass

Why a single straight boundary cannot solve some problems, how stacking neurons into layers fixes it, why activation functions are essential, and how backpropagation trains a small network, all in tested NumPy code.

Log in to take the quiz

Free account · see your score, answers and explanations, earn XP

  1. Question 1

    Why can logistic regression not learn XOR?

  2. Question 2

    What does a single neuron compute?

  3. Question 3

    What does this print?

    import numpy as np
    z = np.array([-2.0, 0.0, 3.0])
    print(np.maximum(0, z))
    
  4. Question 4

    A network has 5 layers but no activation functions. How powerful is it?

  5. Question 5

    In the hand-built XOR network, which two rules do the hidden neurons compute?

🎯 Today’s placement challenge — 10 questions, no login. Can you score 10/10?Take today’s challenge →