Unverified50% confidenceFactExact time
微软研究院何恺明等人于2015年提出残差连接（Residual Connection），使训练超过100层乃至1000层的极深神经网络成为可能
1
Sources
50%
Confidence
Long-term
Relevance
7/20/2026
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.75% 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70% similarUnverified2018年DeepMind团队在《Nature》发表论文，展示训练执行路径积分任务的循环神经网络内部单元自发形成类似生物网格细胞的六角形放电模式70% similarUnverifiedWork by Shwartz-Ziv and Tishby in 2017 showed that deep network training has two phases: first fitting the data (increasing mutual information with the input), then compressing the representation (reducing mutual information with the input while preserving mutual information with the output).69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/571300API
curl https://kongchang.com/api/v1/knowledge/claims/571300MCP
get_claim(id=571300)