Abstract: We consider deep neural networks (DNNs) with a Lipschitz continuous activation function and with weight matrices of variable widths. We establish a uniform convergence analysis framework in ...

1 Department of Mathematics, Binzhou University, Shandong, China. 2 Department of Mathematics, Neijiang Normal University, Sichuan, China. of functions [1] - [7] , computing the n-th iterate of ...

Abstract: In this paper we address the identification problem of a continuous-time deterministic system. We consider that the continuous-time system can be approximated by using the orthonormal ...

We show that a locally compact group G has equivalent right and left uniform structures if (and only if) the sets of bounded, complex-valued, right and left uniformly ...

The information contained in a discrete two-way contingency table can be decomposed into three independent components: row marginals, column marginals and cross-product ratios. The log-linear models ...