A Notation and preliminaries
–Neural Information Processing Systems
A.1 Overview of used notation Table 1: Glossary of used notation. We recall some basic results on the approximation of functions by tanh neural networks in this section. Using the notation of the proof of Theorem 3.5 ( SM B.2), it holds that D Section 3.3 and SM A.2, let ( s, 0) ( s, 0) ( s, 0) ( s, 0) ( s, 0) This is made exact in [15, Section 4]. We now highlight the main steps in the proof. ", (B.18) Putting everything together, we find that if CN This is a consequence of [38, Theorem 36] and Lemma D.1 with " N See SM A.2 for an overview of the notation for finite difference operators.
Neural Information Processing Systems
Oct-9-2025, 15:25:44 GMT