A residual neural network (ResNet) is an artificial neural network (ANN). It is a gateless or open-gated variant of the HighwayNet, the first working very deep feedforward neural network with hundreds of layers, much deeper than previous neural networks. Skip connections or shortcuts are used to jump over some layers (HighwayNets may also learn the skip weights themselves through an additional weight matrix for their gates). Typical ResNet models are implemented with double- or triple-layer skips that contain nonlinearities (ReLU) and batch normalization in between.

Residual Network deep learning models used for computer vision applications. It is a Convolutional Neural Network architecture designed to support hundreds or thousands of convolutional layers