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
VerifiedResNet (Residual Network) was proposed by Microsoft Research's He Kaiming team in 2015 and solved the vanishing gradient problem in deep network training by introducing residual connections.78% similarUnverifiedResNet（残差网络）通过跳跃连接解决了深层网络的梯度消失问题，能提取层次化视觉特征76% similarUnverifiedKaiming He's team pushed the ResNet network depth to 152 layers and resolved the degradation problem through residual connections.74% similarVerifiedDeep learning achieved a breakthrough performance in the 2012 ImageNet competition, driving the revival of connectionism70% similarUnverifiedIn 2015, He Kaiming and colleagues at Microsoft Research proposed Residual Connection, making it possible to train extremely deep neural networks of over 100 or even 1,000 layers.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/575975API
curl https://kongchang.com/api/v1/knowledge/claims/575975MCP
get_claim(id=575975)