On the approximation of functions by tanh neural networks

Samuel Lanthaler; Siddhartha Mishra; Tim De Ryck

REVIEW

On the approximation of functions by tanh neural networks

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2104.08938 v2 pith:F3L5X5BN submitted 2021-04-18 math.NA cs.LGcs.NA

On the approximation of functions by tanh neural networks

Tim De Ryck , Samuel Lanthaler , Siddhartha Mishra This is my paper

classification math.NA cs.LGcs.NA

keywords networksneuralapproximationfunctionsboundserrortanhactivation

verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved

0 comments

read the original abstract

We derive bounds on the error, in high-order Sobolev norms, incurred in the approximation of Sobolev-regular as well as analytic functions by neural networks with the hyperbolic tangent activation function. These bounds provide explicit estimates on the approximation error with respect to the size of the neural networks. We show that tanh neural networks with only two hidden layers suffice to approximate functions at comparable or better rates than much deeper ReLU neural networks.

On the approximation of functions by tanh neural networks

discussion (0)