A differentiable fractional Fourier transform (FRFT) implementation with layers that can be trained end-to-end with the rest of the network. This package provides implementations of both fast ...
Abstract: Modern deep convolutional neural networks (CNNs) suffer from high computational complexity due to excessive convolution operations. Recently, fast convolution algorithms such as fast Fourier ...
Peter Grünberg Institut (PGI-1) and Institute of Advanced Simulations (IAS-1), Forschungszentrum Jülich GmbH and JARA, Jülich 52425, Germany ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results