Limitations of the approximation capabilities of neural networks with one hidden layer

This publication has 14 references indexed in Scilit:

• Neural Networks for Optimal Approximation of Smooth and Analytic Functions
  Neural Computation, 1996
• Regularization Theory and Neural Networks Architectures
  Neural Computation, 1995
• Neural networks for localized approximation
  Mathematics of Computation, 1994
• Universal approximation bounds for superpositions of a sigmoidal function
  IEEE Transactions on Information Theory, 1993
• Approximation properties of a multilayered feedforward artificial neural network
  Advances in Computational Mathematics, 1993
• Multilayer feedforward networks with a nonpolynomial activation function can approximate any function
  Neural Networks, 1993
• Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks
  Neural Networks, 1990
• Approximation by superpositions of a sigmoidal function
  Mathematics of Control, Signals, and Systems, 1989
• Optimal nonlinear approximation
  manuscripta mathematica, 1989
• Fast Learning in Networks of Locally-Tuned Processing Units
  Neural Computation, 1989