The derivative of the ReLU function is
AAlways equal to 1 for all real x
BEqual to sigmoid(x) at every point
C1 if x > 0 and 0 if x < 0
DAlways equal to ReLU(x) itself
Answer & Solution
Correct answer: C. 1 if x > 0 and 0 if x < 0
d/dx ReLU(x) is 0 for x < 0 and 1 for x > 0. At x = 0 the derivative is technically undefined; in practice the left-hand value of 0 is used.
Related questions
Why are sigmoids still used in recurrent networks (e.g., LSTMs) even after ReLU's rise?A 'thresholding' activation taking 0 or 1 cleanly is impractical for gradient-based learniDepth often beats width for the same expressive power becauseWhy is the sigmoid prone to the vanishing-gradient problem?For an MLP layer with input X ∈ ℝⁿˣᵈ, hidden width h and output q, the weight shapes areParametrised ReLU (pReLU) adds which capability over plain ReLU?Why has ReLU largely replaced sigmoid in hidden layers?The universal approximation theorem (Cybenko 1989) for MLPs states that