ConferenceAAAI Conference on Artificial Intelligence2017Featured
Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning
Christian Szegedy, Sergey Ioffe, Vincent Vanhoucke, et al.
This paper demonstrates that residual connections accelerate Inception network training and improve accuracy, achieving 3.08% top-5 error on ImageNet with an ensemble.
16kFeb 12, 2017Scaling Laws
arXiv