Verified70% confidenceFactExact time
The 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.
4
Sources
70%
Confidence
Long-term
Relevance
7/15/2026
First Seen
Sources
AI大模型入门：核心概念、发展历程与国产模型格局
Related Claims
UnverifiedSigmoid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80% similarUnverifiedsigmoid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77% similarUnverifiedThe Tanh function has an output range of -1 to 1 and likewise suffers from the vanishing gradient problem.76% similarUnverifiedExcessively large weights may cause the Sigmoid activation function to saturate, triggering vanishing gradients.72% 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.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/518284API
curl https://kongchang.com/api/v1/knowledge/claims/518284MCP
get_claim(id=518284)