Training of time series patterns using recurrent neural networks based on the extended kalman filter

摘要

Recent study, the extended Kalman filter (EKF) is applied to the learning algorithm for a feedforward neural network and it is shown that the EKF based learning algorithm has good con- vergence performances. However, the feedforward neural network could not perform a dynamic signal processing such as time series pattern recognition. On the other hand, the recurrent neural networks (RNN) could have dynamical characteristics because the RNN has feedback connections with time delay in the network.