Extension of localised approximation by neural networks

DOI10.1017/S0004972700032676zbMath0931.41015MaRDI QIDQ4243358

Bum Il Hong, Nahmwoo Hahm

Publication date: 21 February 2000

Published in: Bulletin of the Australian Mathematical Society (Search for Journal in Brave)

zbMATH Keywords

neural networks

Mathematics Subject Classification ID

Minimal systems representations (93B20) Multidimensional problems (41A63) Approximation with constraints (41A29) Approximation by polynomials (41A10) Approximation by arbitrary nonlinear expressions; widths and entropy (41A46)

Related Items (5)

Approximation error of single hidden layer neural networks with fixed weights ⋮ Computing the Approximation Error for Neural Networks with Weights Varying on Fixed Directions ⋮ A Single Hidden Layer Feedforward Network with Only One Neuron in the Hidden Layer Can Approximate Any Univariate Function ⋮ An approximation by neural networks with a fixed weight ⋮ Approximation order to a function in \(\overline C({\mathbb R})\) by superposition of a sigmoidal function

Cites Work

• Unnamed Item
• Approximation by Ridge functions and neural networks with one hidden layer
• Approximation properties of a multilayered feedforward artificial neural network
• Limitations of the approximation capabilities of neural networks with one hidden layer
• Neural Networks for Functional Approximation and System Identification
• Universal approximation bounds for superpositions of a sigmoidal function
• Neural Networks for Localized Approximation

This page was built for publication: Extension of localised approximation by neural networks