Unverified50% confidenceFactExact time
sigmoid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
1
Sources
50%
Confidence
Long-term
Relevance
7/14/2026
First Seen
Sources
机器学习数学基础学习路线：四大核心板块与资源推荐
Related Claims
VerifiedThe 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.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.77% 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70% similarUnverifiedVanishing 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.65% similarUnverifiedThe ReLU activation function is defined as f(x) = max(0, x); it is computationally simple, does not suffer from the vanishing gradient problem, and has made training deeper networks possible.65% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/503893API
curl https://kongchang.com/api/v1/knowledge/claims/503893MCP
get_claim(id=503893)