A counterexample regarding "New study on neural networks: The essential order of approximation".

Neural networks Rates of convergence Sharpness of error bounds

Journal

Neural networks : the official journal of the International Neural Network Society
ISSN: 1879-2782
Titre abrégé: Neural Netw
Pays: United States
ID NLM: 8805018

Informations de publication

Date de publication:
03 2020
Historique:
received: 24 10 2019
revised: 17 11 2019
accepted: 10 12 2019
pubmed: 31 12 2019
medline: 23 6 2020
entrez: 31 12 2019
Statut: ppublish

Résumé

The paper "New study on neural networks: the essential order of approximation" by Jianjun Wang and Zongben Xu, which appeared in Neural Networks 23 (2010), deals with upper and lower estimates for the error of best approximation with sums of nearly exponential type activation functions in terms of moduli of smoothness. In particular, the presented lower bound is astonishingly good. However, the proof is incorrect and the bound is wrong.

Identifiants

pubmed: 31887683
pii: S0893-6080(19)30399-5
doi: 10.1016/j.neunet.2019.12.007
pii:
doi:

Types de publication

Letter Comment

Langues

eng

Sous-ensembles de citation

IM

Pagination

234-235

Commentaires et corrections

Type : CommentOn

Informations de copyright

Copyright © 2019 Elsevier Ltd. All rights reserved.

Auteurs

Steffen Goebbels (S)

Niederrhein University of Applied Sciences, Faculty of Electrical Engineering and Computer Science, Institute for Pattern Recognition, D-47805 Krefeld, Germany. Electronic address: steffen.goebbels@hsnr.de.

Articles similaires

Unsupervised learning for real-time and continuous gait phase detection.

Dollaporn Anopas, Yodchanan Wongsawat, Jetsada Arnin
1.00
Humans Gait Neural Networks, Computer Unsupervised Machine Learning Walking
Humans Shoulder Fractures Tomography, X-Ray Computed Neural Networks, Computer Female
Humans Artificial Intelligence Neoplasms Prognosis Image Processing, Computer-Assisted
Humans Deep Learning Mouth Neoplasms Drug Resistance, Neoplasm Cell Line, Tumor

Classifications MeSH