Lower estimation of approximation rate for neural networks

DOI10.1007/S11432-009-0027-7zbMath1192.68506OpenAlexW1999902962MaRDI QIDQ848260

Feilong Cao, Yongquan Zhang, Zong Ben Xu

Publication date: 3 March 2010

Published in: Science in China. Series F (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11432-009-0027-7

zbMATH Keywords

approximationratefeedforward neural networkslowertopology structure of hidden layer

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Cites Work

• 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
• On best approximation by ridge functions
• Approximation problems in system identification with neural networks
• 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
• Simultaneous approximations of multivariate functions and their derivatives by neural networks with one hidden layer
• Simultaneous \(\mathbf L^p\)-approximation order for neural networks
• Universal approximation bounds for superpositions of a sigmoidal function
• Dimension-independent bounds on the degree of approximation by neural networks
• Bounds on rates of variable-basis and neural-network approximation
• Comparison of worst case errors in linear and neural network approximation
• Improved rates and asymptotic normality for nonparametric neural network estimators
• Efficient estimation of neural weights by polynomial approximation
• Approximation by superpositions of a sigmoidal function

This page was built for publication: Lower estimation of approximation rate for neural networks