Expired80% confidenceFactExact time
The Sigmoid function has a vanishing gradient problem: when the absolute value of the input is large, its derivative approaches 0, causing the gradient to decay layer by layer during backpropagation.
8
Sources
80%
Confidence
Medium-term (~90 days)
Relevance
7/2/2026
First Seen
Valid until: 9/30/2026(expired)
Sources
Neural Networks from Scratch: A Deep Dive into the Fundamentals from Linear Regression to Gradient Descent
bilibiliAI课堂6/11/2026
Related Claims
Unverifiedsigmoid激活函数的导数最大值仅为0.25，多层连乘后导致梯度迅速消失82% similarVerifiedThe vanishing gradient problem originates from saturating activation functions such as Sigmoid or Tanh, whose derivatives approach zero for large or small input values, causing gradients to decay layer by layer.79% similarUnverifiedSigmoid将输出压缩到0~1之间，Tanh是早期常用激活函数，但随网络层数加深会导致梯度消失问题76% similarUnverifiedCompared to Sigmoid or Tanh activation functions, ReLU has a constant gradient of 1 on the positive half-axis, effectively alleviating the vanishing gradient problem in deep network training, while also having extremely low computational cost.67% similarVerifiedVanishing gradient refers to the exponential decay of gradient values during backpropagation in deep neural networks, causing parameters near the input layer to receive almost no updates.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/47623API
curl https://kongchang.com/api/v1/knowledge/claims/47623MCP
get_claim(id=47623)