Almost everywhere approximation capabilities of double Mellin approximate identity neural networks

DOI10.1007/s00500-015-1753-yzbMath1369.93066OpenAlexW838923821MaRDI QIDQ2403275

Saeed Panahian Fard, Zarita Zainuddin

Publication date: 8 September 2017

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

Full work available at URL: https://doi.org/10.1007/s00500-015-1753-y

zbMATH Keywords

almost everywhere convergenceepsilon-netalmost everywhere approximationdouble Mellin approximate identitydouble Mellin approximate identity neural networksdouble Mellin convolution

Mathematics Subject Classification ID

Related Items (1)

Estimates for the neural network operators of the max-product type with continuous and \(p\)-integrable functions

Cites Work

• The pricing of vulnerable options with double Mellin transforms
• On the approximation by neural networks with bounded number of neurons in hidden layers
• The universal approximation capabilities of double \(2\pi\)-periodic approximate identity neural networks
• Bivariate Mellin convolution operators: quantitative approximation theorems
• Approximation by neural networks with weights varying on a finite set of directions
• Multilayer feedforward networks are universal approximators
• New study on neural networks: the essential order of approximation
• Interpolation by neural network operators activated by ramp functions
• Approximation in weighted \(p\)-mean by RBF networks of Delsarte translates
• The new approximation operators with sigmoidal functions
• The moments of the bivariate Mellin–Picard-type kernels and applications
• Asymptotic formulae for bivariate Mellin convolution operators
• Advances in Neural Networks – ISNN 2005
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Almost everywhere approximation capabilities of double Mellin approximate identity neural networks