Artificial neural networks with uniform norm-based loss functions

DOI10.1007/S10444-024-10124-9MaRDI QIDQ6500165zbMATH OpenFDO

Authors V. Peiris, Vera Roshchina, N. Sukhorukova

Publication date 10 May 2024

Published in Advances in Computational Mathematics (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1007/S10444-024-10124-9

Mathematics Subject Classification ID

Algorithms for approximation of functions (65D15) Numerical optimization and variational techniques (65K10) Nonconvex programming, global optimization (90C26) Minimax problems in mathematical programming (90C47) Applications of mathematical programming (90C90)

Recommendations

• The C-loss function for pattern classification
• A novel multi-scale loss function for classification problems in machine learning
• Application of artificial neural networks in function approximation
• Some aspects of approximation and interpolation of functions artificial neural networks
• Stochastic generalized gradient methods for training nonconvex nonsmooth neural networks

Cites work

• An appropriate subdifferential for quasiconvex functions
• Approximation by superpositions of a sigmoidal function
• Conditions for Convexity of Quasiconvex Functions
• Conjugate quasiconvex nonnegative functions
• DANTE: deep alternations for training neural networks
• Deep learning
• scientific article; zbMATH DE number 3147701 (Why is no real title available?)
• scientific article; zbMATH DE number 1405266 (Why is no real title available?)
• scientific article; zbMATH DE number 2226572 (Why is no real title available?)
• Novel approaches to the discrimination problem
• On functions of three variables
• Optimization for deep learning: an overview
• Sulle stratificazioni convesse

Cited in

(1)

• A novel multi-scale loss function for classification problems in machine learning

This page was built for publication: Artificial neural networks with uniform norm-based loss functions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6500165)