Fourier Convolutions with Kernel Sizes of 1024x1024 and Larger

Multi-dimensional Fourier transformations in convolutional neural networks

Photo by Edz Norton on Unsplash

Convolutional neural networks (CNNs) are widely spread these days. Regardless of their success, convolutions are inefficient. The sliding window requires many computations and limits the size of the kernel. At the same time, a small…