Neural Network Training with Extended Kalman Filter Using Graphics Processing Unit

Authors:
Peter Trebatický;Jiří Pospíchal
Affiliations:
Faculty of Informatics and Information Technologies, Slovak University of Technology in Bratislava, Bratislava, Slovakia 842 16;Faculty of Informatics and Information Technologies, Slovak University of Technology in Bratislava, Bratislava, Slovakia 842 16
Venue:
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II
Year:
2008

Citing 1
Cited 1

Kalman Filtering and Neural Networks

Kalman Filtering and Neural Networks

Training Recurrent Neural Network Using Multistream Extended Kalman Filter on Multicore Processor and Cuda Enabled Graphic Processor Unit

ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part I

Quantified Score

Hi-index	0.00

Visualization

Abstract

The graphics processing unit has evolved through the years into the powerful resource for general purpose computing. We present in this article the implementation of Extended Kalman filter used for recurrent neural networks training, which most computational intensive tasks are performed on the GPU. This approach achieves significant speedup of neural network training process for larger networks.