Fig 6. Hierarchical recurrent ResNet (HRRN) in unfolded form is equivalent to an ultra-deep ResNet.

(a) A hierarchy of convolutional layers with local recurrent connections. This hierarchical structure models the feedforward and local recurrent connections along the hierarchy of ventral visual pathway (e.g. V1, V2, V4, IT). (b) Each recurrent unit is equivalent to a deep ResNet with arbitrary number of layers depending on the unfolding depth. h_t is the layer activity at a specific time (t) and K_t represents a sequence of nonlinear operations (e.g. convolution, batch normalization, and ReLU). [see [63] for more info].