Title :
A cosine-modulated Gaussian activation function for hyper-hill neural networks
Author :
Lee, Sang-Wha ; Moraga, Claudio
Author_Institution :
Dept. of Comput. Sci., Dortmund Univ., Germany
Abstract :
We present here a new class of activation functions for neural networks, which is called the CosGauss function. This function is a cosine-modulated Gaussian function. In contrast to the sigmoidal-, hyperbolic tangent- and Gaussian activation functions, more ridges can be obtained by the CosGauss function. It is proved that this function can be used to approximate polynomials and step functions. The CosGauss function was tested with a cascade-correlation-network on the sonar problem and results are compared with those obtained with other activation functions
Keywords :
Gaussian processes; approximation theory; correlation methods; feedforward neural nets; modulation; multilayer perceptrons; polynomials; sonar signal processing; transfer functions; Gaussian activation function; cascade-correlation-network; cosine-modulated Gaussian activation function; hyperbolic tangent activation function; hyperhill neural networks; multilayer feedforward neural network; polynomial approximation; sigmoidal activation functions; sonar signals; step function approximation; Computer networks; Computer science; Electronic mail; Feedforward neural networks; Frequency; Multi-layer neural network; Neural networks; Polynomials; Sonar; Testing;
Conference_Titel :
Signal Processing, 1996., 3rd International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-2912-0
DOI :
10.1109/ICSIGP.1996.566581
