[KongchangAI]
Unverified50% confidenceFactExact time

ResNet(2015,He 等人)通过引入跳跃连接构造恒等映射的学习旁路,将可训练网络深度推进至 152 层乃至千层,并在 ImageNet 上以显著优势夺冠

1
Sources
50%
Confidence
Long-term
Relevance
7/21/2026
First Seen

Sources

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/575975
API
curl https://kongchang.com/api/v1/knowledge/claims/575975
MCP
get_claim(id=575975)