Unverified60% confidenceFactExact time
The convolution operation itself is translation equivariant — when the input is shifted, the output shifts in the same way.
2
Sources
60%
Confidence
Long-term
Relevance
8/8/2026
First Seen
Sources
谱池化详解：从频域视角重新理解CNN下采样机制
Related Claims
UnverifiedThe convolution operation itself is translation equivariant, whereas classification tasks typically require translation invariance.75% similarUnverifiedThe Looped Transformer repeatedly calls the same set of layers in a loop, thereby inserting far more serial computation steps between two text outputs than in a conventional forward pass.66% similarUnverifiedConverting floating-point numbers to strings must satisfy round-trip consistency, meaning the converted string must parse back to exactly the same binary value when re-parsed as a floating-point number.65% similarUnverifiedConverting integers to floating-point, performing floating-point division, and converting back to integers adds the overhead of two type conversions, but in certain scenarios the overall throughput is actually better.64% similarUnverifiedBackpropagation is essentially a special case of reverse-mode automatic differentiation; for a function with n input parameters and 1 scalar output, all partial derivatives can be computed with just one backward pass.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/709916API
curl https://kongchang.com/api/v1/knowledge/claims/709916MCP
get_claim(id=709916)