Towards a more efficient and costsensitive extreme learning machine: A state-of-the-art review of recent trend

Alaba, Peter Adeniyi and Popoola, Segun I. and Olatomiwa, Lanre and Akanle, M.B. and Ohunakin, O.S. and Adetiba, E. and Alex, Opeoluwa David and Atayero, A. A. and Daud, Wan Mohd Wan (2019) Towards a more efficient and costsensitive extreme learning machine: A state-of-the-art review of recent trend. Neurocomputing, 350. pp. 70-90.

PDF Download (185kB)

Abstract

In spite of the prominence of extreme learning machine model, as well as its excellent features such as insignificant intervention for learning and model tuning, the simplicity of implementation, and high learning speed, which makes it a fascinating alternative method for Artificial Intelligence, including Big Data Analytics, it is still limited in certain aspects. These aspects must be treated to achieve an effective and cost-sensitive model. This review discussed the major drawbacks of ELM, which include difficulty in determination of hidden layer structure, prediction instability and Imbalanced data distributions, the poor capability of sample structure preserving (SSP), and difficulty in accommodating lateral inhibition by direct random feature mapping. Other drawbacks include multi-graph complexity, global memory size, one-by-one or chuck-by-chuck (a block of data), global memory size limitation, and challenges with big data. The recent trend proposed by experts for each drawback is discussed in detail towards achieving an effective and cost-sensitive model.

Item Type:	Article
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions:	Faculty of Engineering, Science and Mathematics > School of Electronics and Computer Science
Depositing User:	nwokealisi
Date Deposited:	07 Nov 2024 14:46
Last Modified:	07 Nov 2024 14:46
URI:	http://eprints.covenantuniversity.edu.ng/id/eprint/18571

Actions (login required)

View Item