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% similarUnverifiedIn "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.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)