Extended Kalman filter-based pruning method for recurrent neural networks
Neural Computation
Kalman Filtering and Neural Networks
Kalman Filtering and Neural Networks
An Introduction to the Kalman Filter
An Introduction to the Kalman Filter
Modeling word perception using the Elman network
Neurocomputing
Evolving neural network using real coded genetic algorithm for daily rainfall-runoff forecasting
Expert Systems with Applications: An International Journal
Singular value decomposition on GPU using CUDA
IPDPS '09 Proceedings of the 2009 IEEE International Symposium on Parallel&Distributed Processing
Reliability-based approach to the inverse kinematics solution of robots using Elman's networks
Engineering Applications of Artificial Intelligence
Recursive Bayesian recurrent neural networks for time-series modeling
IEEE Transactions on Neural Networks
Parallel implementations of recurrent neural network learning
ICANNGA'09 Proceedings of the 9th international conference on Adaptive and natural computing algorithms
Parallel implementation of Artificial Neural Network training for speech recognition
Pattern Recognition Letters
IEEE Transactions on Neural Networks
Survey: Reservoir computing approaches to recurrent neural network training
Computer Science Review
A Hybrid Neurogenetic Approach for Stock Forecasting
IEEE Transactions on Neural Networks
IEEE Transactions on Neural Networks
Convergence Study in Extended Kalman Filter-Based Training of Recurrent Neural Networks
IEEE Transactions on Neural Networks
Hi-index | 0.01 |
Accurately and rapidly predicting a time series is a hot research issue in the current applied sciences field. Compared to gradient-based methods, the existing extended Kalman filter (EKF)-based recurrent neural network (RNN) improved the convergence rate of training, but its computing for the Jacobian matrix was usually complicated and time-consuming. In this study, considering the structural feature of the Elman network and the modeling demand in industrial application, a new direct calculation of the Jacobian matrix for Elman networks is proposed and the corresponding matrix solution is clearly derived, which greatly simplifies the solving process and helps to realize its parallelization. Given the industrial real-time demand, a parallelized method is then reported to model the Elman network, which shifts the computational intensive tasks of network training on graphics processing unit (GPU) for the modeling efficiency. To demonstrate the performance of the proposed method, a number of experimental instances are presented, including the Mackey-Glass time series with additive Gaussian white noise and a real-world industrial application-byproduct gas flow prediction in the steel industry. The results indicate that the proposed method exhibits the merits of rapid modeling, strong generalization and good stability.