论文信息 - Approximation by neural networks with a bounded number of nodes at each level

Approximation by neural networks with a bounded number of nodes at each level

It is shown that the general approximation property of feed-forward multilayer perceptron networks can be achieved in networks where the number of nodes in each layer is bounded, but the number of layers grows to infinity. This is the case provided the node function is twice continuously differentiable and not linear.

G. Gripenberg | G. Gripenberg

[1] Jacques de Villiers,et al. Backpropagation neural nets with one and two hidden layers , 1993, IEEE Trans. Neural Networks.

[2] Y. Makovoz. Uniform Approximation by Neural Networks , 1998 .

[3] Martin Burger,et al. Error Bounds for Approximation with Neural Networks , 2001, J. Approx. Theory.

[4] G. Lorentz,et al. Constructive approximation : advanced problems , 1996 .

[5] Ah Chung Tsoi,et al. Universal Approximation Using Feedforward Neural Networks: A Survey of Some Existing Methods, and Some New Results , 1998, Neural Networks.

[6] Allan Pinkus,et al. Lower bounds for approximation by MLP neural networks , 1999, Neurocomputing.

[7] Alexander N. Gorban,et al. Approximation of continuous functions of several variables by an arbitrary nonlinear continuous function of one variable, linear functions, and their superpositions , 1998 .

[8] Allan Pinkus,et al. Approximation theory of the MLP model in neural networks , 1999, Acta Numerica.

[9] Allan Pinkus,et al. Multilayer Feedforward Networks with a Non-Polynomial Activation Function Can Approximate Any Function , 1991, Neural Networks.

[10] Shin'ichi Tamura,et al. Capabilities of a four-layered feedforward neural network: four layers versus three , 1997, IEEE Trans. Neural Networks.