Sequence Prediction using Spectral RNNs
This work addresses efficiency challenges in embedded and mobile applications, but appears incremental as it builds on existing Fourier and RNN techniques.
The authors tackled the problem of efficient sequence prediction under memory and computational constraints by combining Fourier methods with recurrent neural networks, achieving results on chaotic and real-world datasets.
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.