Unverified50% confidenceFactExact time
Flattening a matrix and feeding it to an MLP results in a non-fixed input dimension due to variable row counts, and breaks permutation invariance.
1
Sources
50%
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
UnverifiedLow-rank decomposition and quantization compression are orthogonally complementary dimensions; quantizing the smaller matrices A and B separately results in smaller errors, and the combined compression ratio can reach several times that of either method alone68% similarUnverifiedIn class-imbalanced scenarios, accuracy alone can be misleading and needs to be combined with a confusion matrix for more fine-grained evaluation.67% similarUnverifiedThe standard approach for handling non-square cost matrices is to pad them into square matrices using large dummy cost values.67% similarUnverified收缩自编码器通过惩罚编码器Jacobian矩阵的Frobenius范数，迫使模型对输入的微小扰动不敏感66% similarUnverifiedThe Hunyuan model tends to oversimplify and smooth, with noticeable jagged artifacts, indicating that resolution is still insufficient.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/556704API
curl https://kongchang.com/api/v1/knowledge/claims/556704MCP
get_claim(id=556704)