The derivative of sigmoid(x) equals
Atanh(x)² with no scaling
Bmax(0, sigmoid(x)) elementwise
Csigmoid(x) · (1 - sigmoid(x))
D1 - sigmoid(x)²
Answer & Solution
Correct answer: C. sigmoid(x) · (1 - sigmoid(x))
d/dx sigmoid(x) = sigmoid(x)·(1 − sigmoid(x)). It reaches a maximum of 0.25 at x = 0 and vanishes as |x| grows — the classic vanishing-gradient source.
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