Unverified50% confidenceFactExact time
Residual connections were first introduced into deep learning by He Kaiming in ResNet in 2015.
1
Sources
50%
Confidence
Long-term
Relevance
9/6/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedDeep learning achieved a breakthrough performance in the 2012 ImageNet competition, driving the revival of connectionism77% 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.75% similarUnverifiedIn 2015, Kaiming He et al. published the paper 'Deep Residual Learning for Image Recognition' at Microsoft Research, formally proposing the ResNet architecture.75% similarVerifiedDQN was proposed by DeepMind in 2013 and was the first to combine deep neural networks with Q-learning.74% similarUnverified2017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74% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/865379API
curl https://kongchang.com/api/v1/knowledge/claims/865379MCP
get_claim(id=865379)