Convolutional Neural Networks

FractalNet

Introduced by Larsson et al. in FractalNet: Ultra-Deep Neural Networks without Residuals

FractalNet is a type of convolutional neural network that eschews residual connections in favour of a "fractal" design. They involve repeated application of a simple expansion rule to generate deep networks whose structural layouts are precisely truncated fractals. These networks contain interacting subpaths of different lengths, but do not include any pass-through or residual connections; every internal signal is transformed by a filter and nonlinearity before being seen by subsequent layers.

Source: FractalNet: Ultra-Deep Neural Networks without Residuals

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Object Recognition 1 50.00%
Image Classification 1 50.00%

Categories