The Estimate for Approximation Error of Neural Network with Two Weights
The neural network with two weights is constructed and its approximation ability to any continuous functions is proved. For this neural network, the activation function is not confined to the odd functions. We prove that it can limitlessly approach any continuous function from limited close subset o...
Main Authors: | Fanzi Zeng, Yuting Tang |
---|---|
Format: | Article |
Language: | English |
Published: |
Hindawi Limited
2013-01-01
|
Series: | The Scientific World Journal |
Online Access: | http://dx.doi.org/10.1155/2013/935312 |
Similar Items
-
The Construction and Approximation of the Neural Network with Two Weights
by: Zhiyong Quan, et al.
Published: (2014-01-01) -
Multichannel Broadcast Based on Home Channel for Cognitive Radio Sensor Networks
by: Fanzi Zeng, et al.
Published: (2014-01-01) -
The Generalization Error Bound for the Multiclass Analytical Center Classifier
by: Zeng Fanzi, et al.
Published: (2013-01-01) -
Signed-Power-of-Two (SPT) Neuron Design and Synapse Weight Approximation for Embedded Neural Networks
by: LIN, CHI-YOU, et al.
Published: (2017) -
Error Estimates for Stabilized Approximation Methods for Semigroups
by: McAllister, Sarah Campbell
Published: (2005)