Abstract
Determining the Weights of A Fourier Series Neural Network on the Basis of the Multidimensional Discrete Fourier TransformThis paper presents a method for training a Fourier series neural network on the basis of the multidimensional discrete Fourier transform. The proposed method is characterized by low computational complexity. The article shows how the method can be used for modelling dynamic systems.
Subject
Applied Mathematics,Engineering (miscellaneous),Computer Science (miscellaneous)
Reference18 articles.
1. Fast Fourier transforms for nonequispaced data;A. Dutt;Journal of Scientific Computing,1993
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献
1. Modern Neural Methods for Function Approximation;Issues in the Use of Neural Networks in Information Retrieval;2016-09-29
2. Regularization of orthogonal neural networks using fractional derivatives;2009 IEEE Youth Conference on Information, Computing and Telecommunication;2009-09