Unverified50% confidenceFactExact time
The residual connection (Residual Connection) proposed by Kaiming He solved the problem of deep loss or collapse caused by too many layers in deep learning.
1
Sources
50%
Confidence
Long-term
Relevance
9/20/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedFocal Loss is used to address the class imbalance problem in deep learning.75% similarUnverifiedIn deep networks, traditional single residual connections still suffer from the vanishing gradient problem, resulting in limited effective information learned by deeper layers.74% similarUnverified残差连接与层归一化解决了深层网络训练不稳定的问题，使模型可堆叠到数十层73% similarUnverifiedResidual connections were first introduced into deep learning by He Kaiming in ResNet in 2015.72% similarUnverifiedThe information bottleneck hypothesis proposed by Shwartz-Ziv and Tishby attempts to explain why deep learning works from the perspective of information compression71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/936598API
curl https://kongchang.com/api/v1/knowledge/claims/936598MCP
get_claim(id=936598)