Unverified50% confidenceFactExact time
当需要表征的特征数量远超可用神经元数量时,网络会利用高维空间中近似正交向量数量远超维度数量的特性(Johnson-Lindenstrauss引理)将多个特征叠加压缩编码到同一组神经元上
1
Sources
50%
Confidence
Long-term
Relevance
7/9/2026
First Seen
Sources
块稀疏特征器:揭开视觉模型神经几何的黑箱
hackernewshackernews7/7/2026
Related Claims
Cite This Claim
Stable URI
https://kongchang.com/claim/313862API
curl https://kongchang.com/api/v1/knowledge/claims/313862MCP
get_claim(id=313862)