Next Article in Journal
Machine Learning Methods for Multiscale Physics and Urban Engineering Problems
Next Article in Special Issue
Utility–Privacy Trade-Off in Distributed Machine Learning Systems
Previous Article in Journal
Fault Diagnosis of Power Transformer Based on Time-Shift Multiscale Bubble Entropy and Stochastic Configuration Network
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Entropy
Volume 24
Issue 8
10.3390/e24081136
entropy-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Analytic Function Approximation by Path-Norm-Regularized Deep Neural Networks

by
Aleksandr Beknazaryan
Institute of Environmental and Agricultural Biology (X-BIO), University of Tyumen, Volodarskogo 6, 625003 Tyumen, Russia
Entropy 2022, 24(8), 1136; https://doi.org/10.3390/e24081136
Submission received: 6 July 2022 / Revised: 11 August 2022 / Accepted: 15 August 2022 / Published: 16 August 2022
(This article belongs to the Special Issue Entropy in Soft Computing and Machine Learning Algorithms II)
Versions Notes

Abstract

We show that neural networks with an absolute value activation function and with network path norm, network sizes and network weights having logarithmic dependence on 1/ε can ε-approximate functions that are analytic on certain regions of Cd.
Keywords: deep neural networks; analytic functions; path norm regularization; exponential convergence deep neural networks; analytic functions; path norm regularization; exponential convergence

Share and Cite

MDPI and ACS Style

Beknazaryan, A. Analytic Function Approximation by Path-Norm-Regularized Deep Neural Networks. Entropy 2022, 24, 1136. https://doi.org/10.3390/e24081136

AMA Style

Beknazaryan A. Analytic Function Approximation by Path-Norm-Regularized Deep Neural Networks. Entropy. 2022; 24(8):1136. https://doi.org/10.3390/e24081136

Chicago/Turabian Style

Beknazaryan, Aleksandr. 2022. "Analytic Function Approximation by Path-Norm-Regularized Deep Neural Networks" Entropy 24, no. 8: 1136. https://doi.org/10.3390/e24081136

APA Style

Beknazaryan, A. (2022). Analytic Function Approximation by Path-Norm-Regularized Deep Neural Networks. Entropy, 24(8), 1136. https://doi.org/10.3390/e24081136

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop