Hands-On Transfer Learning with Python

Residual Neural Networks

In ILSVRC 2015, a novel CNN architecture with skip connections and batch normalization was introduced by Kaiming He and their co-authors from Microsoft Research Asia called the Residual Neural Network (ResNet). With this, they were able to train a neural network with 152 layers (eight times deeper than the VGG network) while still having lower complexity than the VGG network. It achieves a top-5 error rate of 3.57%, which beats human-level performance on this dataset.

The main idea in this architecture is as follows. Instead of hoping that a set of stacked layers would directly fit a desired underlying mapping, H(x), they tried to fit a residual mapping. More formally, they let the stacked set of layers learn the ...