Time Series Prediction with a Weighted Bidirectional Multi-Stream Extended Kalman Filter

Donald C. Wunsch, Missouri University of Science and Technology
Xiao Hu

This document has been relocated to http://scholarsmine.mst.edu/ele_comeng_facwork/1918

There were 7 downloads as of 28 Jun 2016.

Abstract

This paper describes the use of a multi-stream extended Kalman filter (EKF) to tackle the IJCNN 2004 challenge problem - time series prediction on CATS benchmark. A weighted bidirectional approach was adopted in the experiments to incorporate the forward and backward predictions of the time series. EKF is a practical, general approach to neural networks training. It consists of the following: 1) gradient calculation by backpropagation through time (BPTT); 2) weight updates based on the extended Kalman filter; and 3) data presentation using multi-stream mechanics.