File(s) not publicly available
A randomized neural network for data streams
conference contribution
posted on 2023-02-22, 04:15 authored by M Pratama, P P Angelov, J Lu, E Lughofer, M Seera, Chee Peng LimChee Peng LimRandomized 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.
History
Volume
2017-MayPagination
3423 - 3430Publisher DOI
ISBN-13
9781509061815Title of proceedings
Proceedings of the International Joint Conference on Neural NetworksUsage metrics
Categories
No categories selectedKeywords
Science & TechnologyTechnologyComputer Science, Artificial IntelligenceComputer Science, Hardware & ArchitectureEngineering, Electrical & ElectronicComputer ScienceEngineeringEvolving Fuzzy SystemsFuzzy Neural NetworksType-2 Fuzzy SystemsSequential LearningEXTREME LEARNING-MACHINERANDOM WEIGHT NETWORKSALGORITHMS
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC