The universal approximation capabilities of double \(2\pi\)-periodic approximate identity neural networks

DOI10.1007/s00500-014-1449-8zbMath1359.68256OpenAlexW2073269792MaRDI QIDQ521720

Zarita Zainuddin, Saeed Panahian Fard

Publication date: 12 April 2017

Published in: Soft Computing (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s00500-014-1449-8

zbMATH Keywords

uniform convergenceuniversal approximationdouble \(2\pi\)-periodic approximate identitydouble \(2\pi\)-periodic approximate identity neural networksgeneralized Minkowski inequality

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20) Approximation by other special function classes (41A30)

Related Items (6)

The universal approximation capabilities of cylindrical approximate identity neural networks ⋮ An investigation of approximate solutions for second order ordinary differential equations using sigmoid-weighted neural networks ⋮ Almost everywhere approximation capabilities of double Mellin approximate identity neural networks ⋮ Approximate solutions of the Michaelis-Menten nonlinear biochemical reaction model using sigmoid-weighted neural networks ⋮ The universal approximation capabilities of double \(2\pi\)-periodic approximate identity neural networks ⋮ Approximate solutions of fuzzy optimal control problems using sigmoid-weighted neural networks

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Approximation by neural networks with scattered data
• Approximation by neural networks with sigmoidal functions
• Universal approximation by radial basis function networks of Delsarte translates
• The universal approximation capabilities of double \(2\pi\)-periodic approximate identity neural networks
• Multivariate sigmoidal neural network approximation
• Approximation by neural networks with weights varying on a finite set of directions
• The essential order of simultaneous approximation for neural networks
• Mathematics and neural networks -- A glance at some basic connections
• A survey on universal approximation and its limits in soft computing techniques.
• Relaxed conditions for radial-basis function networks to be universal approximators.
• Multilayer feedforward networks are universal approximators
• Function approximation on non-Euclidean spaces
• New study on neural networks: the essential order of approximation
• Approximation properties of a multilayered feedforward artificial neural network
• Neural-network approximation of functions of several variables
• The new approximation operators with sigmoidal functions
• Universal approximation capability of EBF neural networks with arbitrary activation functions
• On the order of approximation by periodic neural networks based on scattered nodes
• Universal Approximation by Ridge Computational Models and Neural Networks: A Survey
• Implications and applications of Kolmogorov's superposition theorem
• Note on a Density Question for Neural Networks
• Universal Approximation of Multiple Nonlinear Operators by Neural Networks
• Approximation by superpositions of a sigmoidal function

This page was built for publication: The universal approximation capabilities of double \(2\pi\)-periodic approximate identity neural networks