Efficient estimation of neural weights by polynomial approximation

DOI10.1109/18.771153MaRDI QIDQ4701411zbMATH OpenOpenAlexFDO

Authors Gunter Ritter

Publication date 21 November 1999

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://semanticscholar.org/paper/17c4913cc4dbdbd190b33ecea330f0b8388aba8b

zbMATH Keywords

algorithmscomplexitypolynomial approximationforward neural networksnearly exponential activation functionneural network with one hidden layerorder of uniform approximationuniform-density problem

Mathematics Subject Classification ID

Computation of special functions and constants, construction of tables (65D20) Learning and adaptive systems in artificial intelligence (68T05) Complexity and performance of numerical algorithms (65Y20) Approximation by polynomials (41A10) Exponential and trigonometric functions (33B10)

Recommendations

• Neural networks for optimal approximation of continuous functions in \(\mathbb R^d\)
• scientific article; zbMATH DE number 1083116
• Neural networks with single hidden layer and the best polynomial approximation
• scientific article; zbMATH DE number 6403124
• Universal approximation bounds for superpositions of a sigmoidal function

Cited in

(16)

• A counterexample regarding ``New study on neural networks: the essential order of approximation
• Efficient calculation of the Gauss-Newton approximation of the Hessian matrix in neural networks
• Perceptrons with polynomial post-processing
• Robust and resource-efficient identification of two hidden layer neural networks
• On sharpness of error bounds for multivariate neural network approximation
• Constructive estimation of approximation for trigonometric neural networks
• Lower estimation of approximation rate for neural networks
• The essential order of approximation for nearly exponential type neural networks
• New study on neural networks: the essential order of approximation
• Towards a mathematical framework to inform neural network modelling via polynomial regression
• Neural computation for robust approximate pole assignment
• MISO multivariate generalized polynomials neural network and its weights-direct-determination
• Parameter redundancy in neural networks: an application of Chebyshev polynomials
• On sharpness of error bounds for univariate approximation by single hidden layer feedforward neural networks
• ReLU neural networks of polynomial size for exact maximum flow computation
• scientific article; zbMATH DE number 1782206 (Why is no real title available?)

This page was built for publication: Efficient estimation of neural weights by polynomial approximation

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4701411)