Parameter redundancy in neural networks: an application of Chebyshev polynomials

DOI10.1007/s10287-006-0009-9zbMath1137.82017OpenAlexW1973639189MaRDI QIDQ2468329

Bruce Curry

Publication date: 22 January 2008

Published in: Computational Management Science (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s10287-006-0009-9

zbMATH Keywords

neural networkChebyshev polynomialparameter redundancymulti layer perceptron neural network (MLP NN) architecture

Mathematics Subject Classification ID

Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Related Items (1)

Neural networks and seasonality: Some technical considerations

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Some remarks on multivariate Chebyshev polynomials
• Testing for neglected nonlinearity in time series models. A comparison of neural network methods and alternative tests
• Multilayer feedforward networks are universal approximators
• Model selection in neural networks: some difficulties
• The Econometric Analysis of Seasonal Time Series
• Universal approximation bounds for superpositions of a sigmoidal function
• A Comparison of “Best” Polynomial Approximations with Truncated Chebyshev Series Expansions

This page was built for publication: Parameter redundancy in neural networks: an application of Chebyshev polynomials