A randomized neural network for data streams

Pratama, Mahardhika and Angelov, Plamen Parvanov and Lu, Jie and Lughofer, Edwin and Seera, Manjeevan and Lim, C. P. (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. ISBN 9781509061839

[thumbnail of IJCNN2017_RNN_manuscript]
Preview
PDF (IJCNN2017_RNN_manuscript)
IJCNN2017_RNN_manuscript.pdf - Accepted Version

Download (314kB)

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.

Item Type:
Contribution in Book/Report/Proceedings
Subjects:
?? neural networkdata stream ??
ID Code:
89207
Deposited By:
Deposited On:
03 Jan 2018 09:10
Refereed?:
Yes
Published?:
Published
Last Modified:
20 Feb 2024 01:29