BulDML at Institute of Mathematics and Informatics >
International Journal ITA >
2004 >
Volume 11 Number 1 >

Please use this identifier to cite or link to this item:

Title: Fourier Neural Networks: An Approach with Sinusoidal Activation Functions
Authors: Mingo, Luis
Aslanyan, Levon
Castellanos, Juan
Díaz, Miguel
Riazanov, Vladimir
Keywords: Neural Networks
Sinusoidal Activation Functions
Issue Date: 2004
Publisher: Institute of Information Theories and Applications FOI ITHEA
Abstract: This paper presents some ideas about a new neural network architecture that can be compared to a Fourier analysis when dealing periodic signals. Such architecture is based on sinusoidal activation functions with an axo-axonic architecture [1]. A biological axo-axonic connection between two neurons is defined as the weight in a connection in given by the output of another third neuron. This idea can be implemented in the so called Enhanced Neural Networks [2] in which two Multilayer Perceptrons are used; the first one will output the weights that the second MLP uses to computed the desired output. This kind of neural network has universal approximation properties [3] even with lineal activation functions.
Description: * Supported by INTAS 2000-626, INTAS YSF 03-55-1969, INTAS INNO 182, and TIC 2003-09319-c03-03.
ISSN: 1313-0463
Appears in Collections:Volume 11 Number 1

Files in This Item:

File Description SizeFormat
ijita11-1-p09.pdf106.5 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.


Valid XHTML 1.0!   Creative Commons License