A fast noise filtering algorithm for time series prediction using recurrent neural networks

07/16/2020
by   Boris Rubinstein, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset