2015-12-10Paper
ResNet: Going Deeper Than Ever
Kaiming He and team at Microsoft introduce Residual Networks with 'skip connections' that allow training of networks with 152+ layers. ResNet won the ImageNet challenge and showed that deeper networks could keep improving, a key insight for scaling AI.
References
- Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
CVPR2016