Training Dynamic Neural Networks Using the Extended Kalman Filter for Multi-Step-Ahead Predictions
DOI10.1007/978-3-319-09903-3_11zbMATH Open1341.68152OpenAlexW963615952MaRDI QIDQ2950101FDOQ2950101
Authors: Artem Chernodub 
Publication date: 8 October 2015
Published in: Springer Series in Bio-/Neuroinformatics (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1007/978-3-319-09903-3_11
Recommendations
- A modified extended Kalman filter method for multi-layered neural network training
- Training radial basis neural networks with the extended Kalman filter
- Learning algorithms of layered neural networks via extended Kalman filters
- Extended and unscented Kalman filtering based feedforward neural networks for time series prediction
- RBF networks training using a dual extended Kalman filter
- Recurrent Neural Network Training With Convex Loss and Regularization Functions by Extended Kalman Filtering
multi-step-ahead predictionbackpropagation through timeforecasted propagation through timemini-batch extended Kalman filter
Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Learning and adaptive systems in artificial intelligence (68T05) Inference from stochastic processes and prediction (62M20)
Cited In (7)
- Multi-step learning rule for recurrent neural models: An application to time series forecasting
- Title not available (Why is that?)
- Extended Kalman filter training of neural networks on a SIMD parallel machine
- A new approach to real‐time training of dynamic neural networks
- Extended and unscented Kalman filtering based feedforward neural networks for time series prediction
- An application of neural networks trained with Kalman filter variants (EKF and UKF) to heteroscedastic time series forecasting
- A modified extended Kalman filter method for multi-layered neural network training
This page was built for publication: Training Dynamic Neural Networks Using the Extended Kalman Filter for Multi-Step-Ahead Predictions
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2950101)
