pith. sign in

arxiv: 1712.08688 · v3 · pith:ZNY2DA7Rnew · submitted 2017-12-23 · 🧮 math.NA · cs.NA

New error bounds for deep networks using sparse grids

classification 🧮 math.NA cs.NA
keywords deeperrorgridsnetworkssparseapproximationboundsconcerning
0
0 comments X
read the original abstract

We prove a theorem concerning the approximation of multivariate functions by deep ReLU networks. We present new error estimates for which the curse of the dimensionality is lessened by establishing a connection with sparse grids.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.