Some Comparisons of Linear and Deep ReLU Network Approximation

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985807%3A_____%2F24%3A00598159" target="_blank" >RIV/67985807:_____/24:00598159 - isvavai.cz</a>

Result on the web

<a href="https://doi.org/10.1007/978-3-031-72359-9_17" target="_blank" >https://doi.org/10.1007/978-3-031-72359-9_17</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-72359-9_17" target="_blank" >10.1007/978-3-031-72359-9_17</a>

Result language

angličtina

Original language name

Some Comparisons of Linear and Deep ReLU Network Approximation

Original language description

Influence of depth of ReLU networks on growth of their non-linearity is studied. Lower bounds on worst-case errors in linear approximation are derived for sets of highly-oscillatory functions that can be exactly represented by ReLU networks. Dependence of these errors on network depth is analyzed.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

<a href="/en/project/GA22-02067S" target="_blank" >GA22-02067S: AppNeCo: Approximate Neurocomputing</a><br>

Continuities

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Publication year

2024

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Artificial Neural Networks and Machine Learning – ICANN 2024. Proceedings, Part X

ISBN

978-3-031-72358-2

ISSN

0302-9743

e-ISSN

—

Number of pages

10

Pages from-to

231-240

Publisher name

Springer

Place of publication

Cham

Event location

Lugano

Event date

Sep 17, 2024

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

001331898500017