A fast noise filtering algorithm for time series prediction using recurrent neural networks
This work addresses efficiency issues in time series prediction for applications requiring fast processing, but it appears incremental as it builds on existing RNN methods.
The paper tackled the problem of slow noise filtering in time series prediction with recurrent neural networks by analyzing their internal dynamics, resulting in a new algorithm that significantly speeds up prediction without accuracy loss.
Recent research demonstrate that prediction of time series by recurrent neural networks (RNNs) based on the noisy input generates a smooth anticipated trajectory. We examine the internal dynamics of RNNs and establish a set of conditions required for such behavior. Based on this analysis we propose a new approximate algorithm and show that it significantly speeds up the predictive process without loss of accuracy.