Читать книгу Artificial Intelligence and Quantum Computing for Advanced Wireless Networks - Savo G. Glisic - Страница 86

Theorem 5.1

Оглавление

(Differentiability) [1] : Let Fw and Gw be the global transition and the global output functions of a GNN, respectively. If Fw(x, l) and Gw(x, lN) are continuously differentiable w.r.t. x and w, then ϕw is continuously differentiable w.r.t. w (for the proof, see [1]).

Artificial Intelligence and Quantum Computing for Advanced Wireless Networks

Подняться наверх