Properties of the Hermite Activation Functions in a Neural Approximation Scheme

Authors:
Bartlomiej Beliczynski
Affiliations:
Warsaw University of Technology, Koszykowa 75, 00-662 Warsaw, Poland
Venue:
ICANNGA '07 Proceedings of the 8th international conference on Adaptive and Natural Computing Algorithms, Part II
Year:
2007

Citing 7
Cited 3

Multilayer feedforward networks are universal approximators

Neural Networks
On the approximate realization of continuous mappings by neural networks

Neural Networks
Regularization theory and neural networks architectures

Neural Computation
Hermite neural network correlation and application

IEEE Transactions on Signal Processing
Constructive algorithms for structure learning in feedforward neural networks for regression problems

IEEE Transactions on Neural Networks
Objective functions for training new hidden units in constructive neural networks

IEEE Transactions on Neural Networks
Constructive feedforward neural networks using Hermite polynomial activation functions

IEEE Transactions on Neural Networks

Several Enhancements to Hermite-Based Approximation of One-Variable Functions

ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Approximation of functions by multivariable hermite basis: a hybrid method

ICANNGA'11 Proceedings of the 10th international conference on Adaptive and natural computing algorithms - Volume Part I
A method of multivariable Hermite basis function approximation

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

The main advantage to use Hermite functions as activation functions is that they offer a chance to control high frequency components in the approximation scheme. We prove that each subsequent Hermite function extends frequency bandwidth of the approximator within limited range of well concentrated energy. By introducing a scalling parameter we may control that bandwidth.