Investigation of fourier features in neural networks and an application to steering in mesh networks

Official URL: https://risc01.sabanciuniv.edu/record=b2486379 _(Table of contents)

Random Fourier features provide one of the most prominent ways to classify largescale data sets when the classification is nonlinear. However, Fourier features, in its original proposal, are randomly drawn from a certain distribution and are not optimized. In this thesis, we investigate the use of Fourier features by a single hidden layer feedforward neural network (SLFN) and optimize those features (instead of drawing randomly) with several gradient-descent based approaches. The optimized Fourier features are deduced from the radial basis function (RBF kernel), and implemented in the hidden layer of the SLFN which is followed by the output layer. The resulting classification accuracy is compared with the results of SVM with RBF kernel. Particularly, (1) we tune the parameters such as the hidden layer size and RBF kernel bandwidth, and (2) test with ten different classification data sets. The introduced SLFN provides substantial computational gains with similar accuracy figures compared to the ones of SVM. We also test our SLFN for steering in wireless mesh networks and observe promising smart steering capabilities