alleryStart learning →Why is the sigmoid prone to the vanishing-gradient problem?
AIts gradient depends on the batch size used
BIts gradient saturates near zero for |x| large
CIts gradient is identically zero across all inputs
DIts gradient grows without bound as x grows
Answer & Solution
Correct answer: B. Its gradient saturates near zero for |x| large
The sigmoid derivative s(x)(1 − s(x)) approaches zero whenever |x| is large (the function saturates near 0 or 1).
Stacking many sigmoid layers multiplies these tiny derivatives, vanishing the gradient.
Keep practising MLP and Activations
Browse all MLP and Activations questions for Claude, or explore more Aifoundations topics.
Related questions
Flip and match each activationFor an MLP layer with input X ∈ ℝⁿˣᵈ, hidden width h and output q, the weight shapes areThe derivative of sigmoid(x) equalsThe derivative of the ReLU function isThe tanh function squashes its input to which interval?The sigmoid function squashes its input to which interval?The ReLU activation function is defined asWhy does a stack of affine layers collapse without an activation function?