Fourier Neural Networks: A Comparative Study

02/08/2019
by   Abylay Zhumekenov, et al.
0

We review neural network architectures which were motivated by Fourier series and integrals and which are referred to as Fourier neural networks. These networks are empirically evaluated in synthetic and real-world tasks. Neither of them outperforms the standard neural network with sigmoid activation function in the real-world tasks. All neural networks, both Fourier and the standard one, empirically demonstrate lower approximation error than the truncated Fourier series when it comes to an approximation of a known function of multiple variables.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset