Unverified70% confidenceFactExact time
Permutation invariance means the output does not change when the input order changes, while permutation equivariance means the output transforms in the same way as the input.
2
Sources
70%
Confidence
Long-term
Relevance
7/19/2026
First Seen
Sources
变长矩阵分类：如何为无序集合数据选择神经网络架构
Related Claims
Unverified等变神经网络的等变性使输出随输入的旋转或平移变换而以相同方式变换，这种归纳偏置提高了样本效率62% similarUnverifiedThe convolution operation itself is translation equivariant — when the input is shifted, the output shifts in the same way.59% similarUnverifiedGPU并行归约操作的浮点累加顺序不固定导致传统Transformer注意力机制的实际输出存在微小的不可复现波动59% similarUnverified在流式响应中途断开重试时，提供商可能已对已生成的token计费，重试意味着重新发送完整输入并重新生成输出，导致重复付费59% similarVerifiedThe Self-Attention mechanism of the standard Transformer requires global computation over the entire input sequence, making it inherently unsuitable for streaming scenarios where input is processed incrementally.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/556711API
curl https://kongchang.com/api/v1/knowledge/claims/556711MCP
get_claim(id=556711)