ResNet (Residual Network)
/ˈrɛznɛt/
A CNN architecture that uses residual connections (skip connections) to enable training of very deep networks.
In italiano: ResNet (Residual Network)ResNet introduced skip connections that allow gradients to flow directly through the network, solving the degradation problem in very deep networks. Variants include ResNet-50, ResNet-101, and ResNet-152.
Examples
- Image classification
- Feature extraction backbone
- Transfer learning base