Abstract: In this article, we propose a set of transform-based neural network layers as an alternative to the $3\,\, {}\times {}3$ Conv2D layers in convolutional neural networks (CNNs). The proposed ...
Abstract: The symmetric binary perceptron (SBP) is a random constraint satisfaction problem (CSP) and a single-layer neural network; it exhibits intriguing features, most notably a sharp phase ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results