A new learning algorithm for diagonal recurrent neural network

Authors:
Deng Xiaolong;Xie Jianying;Guo Weizhong;Liu Jun
Affiliations:
Department of Automation, Shanghai Jiaotong University, Shanghai, China;Department of Automation, Shanghai Jiaotong University, Shanghai, China;Department of Mechanical Engineering, Shanghai Jiaotong University, Shanghai;First Research Institute of Corps of Engineers, General Armaments Department, PLA, Wuxi, Jiangsu, China
Venue:
ICNC'05 Proceedings of the First international conference on Advances in Natural Computation - Volume Part I
Year:
2005

Citing 3
Cited 0

On sequential Monte Carlo sampling methods for Bayesian filtering

Statistics and Computing
Sequential Monte Carlo Methods to Train Neural Network Models

Neural Computation
Diagonal recurrent neural networks for dynamic systems control

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

A new hybrid learning algorithm combining the extended Kalman filter (EKF) and particle filter is presented. The new algorithm is firstly applied to train diagonal recurrent neural network (DRNN). The EKF is used to train DRNN and particle filter applies the resampling algorithm to optimize the particles, namely DRNNs, with the relative network weights. These methods make the training shorter and DRNN convergent more quickly. Simulation results of the nonlinear dynamical identification verify the validity of the new algorithm.