Sequence Prediction Using Spectral RNNs
ICANN (1)(2020)
摘要
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. (Source code available at https://github.com/v0lta/Spectral-RNN).
更多查看译文
关键词
Sequence modelling,Frequency domain,Short time Fourier transform
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络