Constructive approximate interpolation by neural networks

DOI10.1016/j.cam.2005.04.019zbMath1089.65012MaRDI QIDQ817488

Bernardo Llanas, Francisco Javier Sáinz

Publication date: 16 March 2006

Published in: Journal of Computational and Applied Mathematics (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.cam.2005.04.019

zbMATH Keywords

neural networks; uniform approximation; approximate interpolation

Mathematics Subject Classification ID

65D05: Numerical interpolation

41A05: Interpolation in approximation theory

Related Items

Approximation by max-product neural network operators of Kantorovich type, Quasi-interpolation for surface reconstruction from scattered data with radial basis function, Constructive approximate interpolation by neural networks in the metric space, Interpolation and rates of convergence for a class of neural networks, Hermite interpolation by neural networks, Approximation theorems for a family of multivariate neural network operators in Orlicz-type spaces, Neural network operators: constructive interpolation of multivariate functions, Saturation classes for MAX-product neural network operators activated by sigmoidal functions, The construction and approximation of some neural network operators, The errors of approximation for feedforward neural networks in thelpmetric, The new approximation operators with sigmoidal functions, Max-product neural network and quasi-interpolation operators activated by sigmoidal functions, Convergence for a family of neural network operators in Orlicz spaces, The capability of approximation for neural networks interpolant on the sphere

Cites Work

• Feedforward nets for interpolation and classification
• Approximation by superposition of sigmoidal and radial basis functions
• Interpolation by ridge polynomials and its application in neural networks
• Multilayer feedforward networks are universal approximators
• Single-iteration training algorithm for multi-layer feed-forward neural networks
• Nonlinearity creates linear independence
• Limitations of the approximation capabilities of neural networks with one hidden layer
• Neural Networks for Localized Approximation
• Neural Network Learning
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item