Title :
Construction of neural nets using the radon transform
Author :
Carroll, S.M. ; Dickinson, B.W.
Author_Institution :
Dept. of Electr. Eng., Princeton Univ., NJ, USA
Abstract :
The authors present a method for constructing a feedforward neural net implementing an arbitrarily good approximation to any L/sub 2/ function over (-1, 1)/sup n/. The net uses n input nodes, a single hidden layer whose width is determined by the function to be implemented and the allowable mean square error, and a linear output neuron. Error bounds and an example are given for the method.<>
Keywords :
function approximation; neural nets; feedforward neural net; linear output neuron; mean square error; nodes; radon transform; Approximation methods; Neural networks;
Conference_Titel :
Neural Networks, 1989. IJCNN., International Joint Conference on
Conference_Location :
Washington, DC, USA
DOI :
10.1109/IJCNN.1989.118639
