A neural network for forward and inverse nonlinear Fourier transforms for fiber optic communication

We propose a neural network for both forward and inverse continuous nonlinear Fourier transforms, NFT and I<PRE_TAG>NFT</POST_TAG> respectively. We demonstrate the network's capability to perform NFT and I<PRE_TAG>NFT</POST_TAG> for a random mix of NFDM-QAM signals. The network transformations (NFT and I<PRE_TAG>NFT</POST_TAG>) exhibit true characteristics of these transformations; they are significantly different for low and high-power input pulses. The network shows adequate accuracy with an RMSE of 5e-3 for forward and 3e-2 for inverse transforms. We further show that the trained network can be used to perform general nonlinear Fourier transforms on arbitrary pulses beyond the training pulse types.