Unverified50% confidenceFactExact time
ResNet 由何恺明等人在 2015 年提出，核心创新是跳跃连接，让网络学习残差映射 F(x)=H(x)-x
1
Sources
50%
Confidence
Long-term
Relevance
8/28/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedResidual connections were originally proposed by He et al. in the 2015 ResNet paper to address the vanishing gradient problem in deep neural networks.73% similarUnverified残差连接（ResNet）由中国学者何恺明提出，数学表达为 H(x) = F(x) + x65% similarUnverifiedResidual connections were introduced by He et al. in the 2015 ResNet paper, and batch normalization was proposed by Ioffe and Szegedy in 2015.61% similarUnverifiedIn 2002, Kenneth Stanley proposed the NEAT algorithm (NeuroEvolution of Augmenting Topologies), which evolves not only network weights but also network topology.60% similarUnverified2020年MIP*=RE成果证明了量子交互证明系统的能力，同时解决了Connes嵌入猜想这一纯数学问题59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/810811API
curl https://kongchang.com/api/v1/knowledge/claims/810811MCP
get_claim(id=810811)