Unverified50% confidenceFactExact time
Lu等人于2017年证明了宽度有限但深度无限的ReLU网络同样是普适逼近器
1
Sources
50%
Confidence
Long-term
Relevance
8/22/2026
First Seen
Sources
Related Entities
Related Claims
Unverified2017年Guo等人在ICML发表的《On Calibration of Modern Neural Networks》首次大规模实证校准失当现象，发现ResNet等现代深度网络比早期浅层网络校准更差66% similarVerifiedResNet (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training by introducing residual connections.61% similarUnverifiedIn modern deep networks, Sigmoid has gradually been replaced by ReLU and its variants.61% similarUnverifiedKaiming He's team pushed the ResNet network depth to 152 layers and resolved the degradation problem through residual connections.60% similarUnverifiedReLU, defined as max(0, x), rapidly gained widespread adoption in the 2010s due to its computational efficiency and gradient stability, becoming the default activation function in modern deep learning.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/787193API
curl https://kongchang.com/api/v1/knowledge/claims/787193MCP
get_claim(id=787193)