New study on neural networks: the essential order of approximation

DOI10.1016/j.neunet.2010.01.004zbMath1398.65023OpenAlexW2097698789WikidataQ51723412 ScholiaQ51723412MaRDI QIDQ1784569

Zong Ben Xu, Jian-Jun Wang

Publication date: 27 September 2018

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.neunet.2010.01.004

zbMATH Keywords

modulus of smoothnessessential order of approximationnearly exponential type neural networks

Mathematics Subject Classification ID

Algorithms for approximation of functions (65D15)

Related Items

The universal approximation capabilities of cylindrical approximate identity neural networks, Almost everywhere approximation capabilities of double Mellin approximate identity neural networks, Robust exponential synchronization for neutral complex networks with discrete and distributed time-varying delays: A descriptor model transformation method, Hybrid adaptive pinning control for function projective synchronization of delayed neural networks with mixed uncertain couplings, A counterexample regarding ``New study on neural networks: the essential order of approximation, On sharpness of error bounds for multivariate neural network approximation, Global synchronization for hybrid coupled neural networks with interval time-varying delays: A matrix-based quadratic convex approach, Mixed \(H_{\infty }\)/passive exponential function projective synchronization of delayed neural networks with hybrid coupling based on pinning sampled-data control, The universal approximation capabilities of double \(2\pi\)-periodic approximate identity neural networks, On sharpness of error bounds for univariate approximation by single hidden layer feedforward neural networks, The construction and approximation of the neural network with two weights, Crew exploration vehicle (CEV) attitude control using a neural–immunology/memory network, Chaotic synchronisation for coupled neural networks based on T-S fuzzy theory

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• The essential order of approximation for neural networks
• Approximation by Ridge functions and neural networks with one hidden layer
• Approximation by superposition of sigmoidal and radial basis functions
• Multilayer feedforward networks are universal approximators
• Degree of approximation by neural and translation networks with a single hidden layer
• The essential order of approximation for nearly exponential type neural networks
• Universal approximation bounds for superpositions of a sigmoidal function
• Dimension-independent bounds on the degree of approximation by neural networks
• Efficient estimation of neural weights by polynomial approximation
• Approximation by superpositions of a sigmoidal function