Hussein, Shamina and Chandra, Rohitash and Sharma, Anuraganand (2016) Multi-step-ahead chaotic time series predication using coevolutionary recurrent neural networks. [Conference Proceedings]
Full text not available from this repository. (Request a copy)Abstract
Multi-step-ahead time series prediction has been one of the greatest challenges for machine learning. Recurrent neural networks (RNN) can efficiently model temporal sequences and have been promising for multi-step time series prediction. Cooperative neuro-evolution has been used for training RNNs with promising performance for single step ahead time series prediction. This paper employs cooperative neuro-evolution of RNNs for multi-step ahead prediction. The RNN recursively predicts the next values in the horizon where the output from the single-step ahead prediction are the input for predicting the next value in the horizon. The performance of cooperative neuro-evolution is compared with back-propagation through time (BPTT) learning algorithm. The results are promising which shows that cooperative neuro-evolution performs better compared to BPTT for most cases.
Item Type: | Conference Proceedings |
---|---|
Uncontrolled Keywords: | backpropagation;chaos;evolutionary computation;learning (artificial intelligence);recurrent neural nets;time series;multistep-ahead chaotic time series prediction;coevolutionary recurrent neural networks;RNN;cooperative neuro-evolution;single-step ahead prediction;back-propagation through time;BPTT learning algorithm;Time series analysis;Neurons;Recurrent neural networks;Training;Predictive models;Prediction algorithms;Biological neural networks |
Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science Q Science > QA Mathematics > QA76 Computer software |
Divisions: | Faculty of Science, Technology and Environment (FSTE) > School of Computing, Information and Mathematical Sciences |
Depositing User: | Anuraganand Sharma |
Date Deposited: | 02 Jul 2019 22:35 |
Last Modified: | 02 Jul 2019 22:35 |
URI: | https://repository.usp.ac.fj/id/eprint/11606 |
Actions (login required)
View Item |