Fourier methods have a long and proven track record as an excellent tool in data processing. Integrating Fourier methods into complex recurrent neural network architectures is therefore an important goal. I integrated the short-time Fourier transform into a recurrent (complex-valued) network structure. This helps when dealing with hard prediction tasks such as human motion prediction, a demo paper and code are available.

Paper: https://arxiv.org/pdf/1812.05645.pdf

Code: https://github.com/v0lta/Spectral-RNN