Home > Research > Publications & Outputs > A randomized neural network for data streams

Research

Associated organisational units

Electronic data

Links

Text available via DOI:

Keywords

View graph of relations

A randomized neural network for data streams

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

A randomized neural network for data streams. / Pratama, Mahardhika; Angelov, Plamen Parvanov; Lu, Jie et al.
Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN). USA: IEEE, 2017. p. 3423-3430.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Pratama, M, Angelov, PP, Lu, J, Lughofer, E, Seera, M & Lim, CP 2017, A randomized neural network for data streams. in Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN). IEEE, USA, pp. 3423-3430. https://doi.org/10.1109/IJCNN.2017.7966286

APA

Pratama, M., Angelov, P. P., Lu, J., Lughofer, E., Seera, M., & Lim, C. P. (2017). A randomized neural network for data streams. In Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN) (pp. 3423-3430). IEEE. https://doi.org/10.1109/IJCNN.2017.7966286

Vancouver

Pratama M, Angelov PP, Lu J, Lughofer E, Seera M, Lim CP. A randomized neural network for data streams. In Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN). USA: IEEE. 2017. p. 3423-3430 doi: 10.1109/IJCNN.2017.7966286

Author

Pratama, Mahardhika ; Angelov, Plamen Parvanov ; Lu, Jie et al. / A randomized neural network for data streams. Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN). USA : IEEE, 2017. pp. 3423-3430

Bibtex

@inproceedings{d7f9e8ada1e642bdaaacb69416f8d6e4,
title = "A randomized neural network for data streams",
abstract = "Randomized neural network (RNN) is a highly feasible solution in the era of big data because it offers a simple and fast working principle in processing dynamic and evolving data streams. This paper proposes a novel RNN, namely recurrent type-2 random vector functional link network (RT2McRVFLN), which provides a highly scalable solution for data streams in a strictly online and integrated framework. It is built upon the psychologically inspired concept of metacognitive learning, which covers three basic components of human learning: what-to-learn, how-to-learn, and when-to-learn. The what-to-learn selects important samples on the fly with the use of online active learning scenario, which renders our algorithm an online semi-supervised algorithm. The how-to-learn process combines an open structure of evolving concept and a randomized learning algorithm of random vector functional link network (RVFLN). The efficacy of the RT2McRVFLN has been numerically validated through two real-world case studies and comparisons with its counterparts, which arrive at a conclusive finding that our algorithm delivers a tradeoff between accuracy and simplicity.",
keywords = "Neural Network, Data stream",
author = "Mahardhika Pratama and Angelov, {Plamen Parvanov} and Jie Lu and Edwin Lughofer and Manjeevan Seera and Lim, {C. P.}",
year = "2017",
month = may,
day = "19",
doi = "10.1109/IJCNN.2017.7966286",
language = "English",
isbn = "9781509061839",
pages = "3423--3430",
booktitle = "Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN)",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - A randomized neural network for data streams

AU - Pratama, Mahardhika

AU - Angelov, Plamen Parvanov

AU - Lu, Jie

AU - Lughofer, Edwin

AU - Seera, Manjeevan

AU - Lim, C. P.

PY - 2017/5/19

Y1 - 2017/5/19

N2 - Randomized neural network (RNN) is a highly feasible solution in the era of big data because it offers a simple and fast working principle in processing dynamic and evolving data streams. This paper proposes a novel RNN, namely recurrent type-2 random vector functional link network (RT2McRVFLN), which provides a highly scalable solution for data streams in a strictly online and integrated framework. It is built upon the psychologically inspired concept of metacognitive learning, which covers three basic components of human learning: what-to-learn, how-to-learn, and when-to-learn. The what-to-learn selects important samples on the fly with the use of online active learning scenario, which renders our algorithm an online semi-supervised algorithm. The how-to-learn process combines an open structure of evolving concept and a randomized learning algorithm of random vector functional link network (RVFLN). The efficacy of the RT2McRVFLN has been numerically validated through two real-world case studies and comparisons with its counterparts, which arrive at a conclusive finding that our algorithm delivers a tradeoff between accuracy and simplicity.

AB - Randomized neural network (RNN) is a highly feasible solution in the era of big data because it offers a simple and fast working principle in processing dynamic and evolving data streams. This paper proposes a novel RNN, namely recurrent type-2 random vector functional link network (RT2McRVFLN), which provides a highly scalable solution for data streams in a strictly online and integrated framework. It is built upon the psychologically inspired concept of metacognitive learning, which covers three basic components of human learning: what-to-learn, how-to-learn, and when-to-learn. The what-to-learn selects important samples on the fly with the use of online active learning scenario, which renders our algorithm an online semi-supervised algorithm. The how-to-learn process combines an open structure of evolving concept and a randomized learning algorithm of random vector functional link network (RVFLN). The efficacy of the RT2McRVFLN has been numerically validated through two real-world case studies and comparisons with its counterparts, which arrive at a conclusive finding that our algorithm delivers a tradeoff between accuracy and simplicity.

KW - Neural Network

KW - Data stream

U2 - 10.1109/IJCNN.2017.7966286

DO - 10.1109/IJCNN.2017.7966286

M3 - Conference contribution/Paper

SN - 9781509061839

SP - 3423

EP - 3430

BT - Proceedings of the 2017 International Joint Conference on Neural Networks (IJCNN)

PB - IEEE

CY - USA

ER -