English

Sequence Prediction using Spectral RNNs

Machine Learning 2020-08-17 v3 Machine Learning

Abstract

Fourier methods have a long and proven track record as an excellent tool in data processing. As memory and computational constraints gain importance in embedded and mobile applications, we propose to combine Fourier methods and recurrent neural network architectures. The short-time Fourier transform allows us to efficiently process multiple samples at a time. Additionally, weight reductions trough low pass filtering is possible. We predict time series data drawn from the chaotic Mackey-Glass differential equation and real-world power load and motion capture data.

Keywords

Cite

@article{arxiv.1812.05645,
  title  = {Sequence Prediction using Spectral RNNs},
  author = {Moritz Wolter and Juergen Gall and Angela Yao},
  journal= {arXiv preprint arXiv:1812.05645},
  year   = {2020}
}

Comments

Source code available at https://github.com/v0lta/Spectral-RNN

R2 v1 2026-06-23T06:41:57.181Z