Unverified90% confidenceFactTime unknown
高斯模糊的计算量随模糊半径增大呈平方级增长
1
Sources
90%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedThe reason for dividing by √d_k in the Attention formula is to prevent excessively large dot products from causing the softmax gradient to vanish.63% similarVerifiedThe self-attention mechanism causes computational complexity to grow quadratically with sequence length, so expanding the context from 1,000 to 4,000 tokens increases the computation by 16 times.61% similarVerifiedThe generalization error of a model equals the squared bias plus variance plus irreducible noise.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/12228API
curl https://kongchang.com/api/v1/knowledge/claims/12228MCP
get_claim(id=12228)