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
UnverifiedIn "On Calibration of Modern Neural Networks" published at ICML in 2017 by Guo et al., the miscalibration phenomenon was empirically demonstrated at scale for the first time, finding that modern deep networks such as ResNet are worse calibrated than earlier shallow networks.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training by introducing residual connections.61% similarUnverifiedIn modern deep networks, Sigmoid has gradually been replaced by ReLU and its variants.61% similarUnverifiedKaiming He's team pushed the ResNet network depth to 152 layers and resolved the degradation problem through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)