Réseau neuronal résiduel

Domaine

Catégorie Démo Apprentissage profond

Anglais

ResNet

Deep Residual Networks won the ILSVRC 2015 challenge. These networks work by introducing shortcut connection across stacks of layers, allowing the optimizer to learn “easier” residual mappings instead of the more complicated original mappings. These shortcut connections are similar to Highway Layers, but they are data-independent and don’t introduce additional parameters or training complexity. ResNets achieved a 3.57% error rate on the ImageNet test set. • Deep Residual Learning for Image Recognition