Abstract: In this paper, we first provide some properties of truth tables of bent functions. Furthermore, a upper bound of truth table's runs length of a bent function is presented. Based on these ...
Abstract: Activation functions provide deep neural networks the non-linearity that is necessary to learn complex distributions. It is still inconclusive what is the optimal shape for the activation ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results