Analysis of Extreme Learning Machine Based on Multiple Hidden Layers

Authors

  • M.Vinoth Kumar Associate professor, Department of Information Science and Engineering, RV Institute of Technology and Management, Bangalore-560076
  • G. Kiran Kumar Assistant Professor, Computer Science Data Science, Madanapalle Institute of Technology & Science
  • Ahmed Mudassar Ali Director, MEASI Institute of Information Technology
  • S.K. Rajesh Kanna Professor, Mechanical Engineering Department, Rajalakshmi Institute of Technology
  • K. Muthu Lakshmi Associate Professor, Department of Information Technology, Panimalar Engineering College

Keywords:

automated programmes, machine learning, intelligent systems, industry

Abstract

Humans can process vast volumes of data, learn about the behavior of the data, and make better decisions based on the analysis that results from machine learning (ML). ML has uses in many different domains. DL and ML techniques have gained widespread recognition and are being used in many real-time engineering applications due to their remarkable performance. To create intelligent and automated programs that can manage data in fields like cyber-security, health, and intelligent schemes, one must possess a solid understanding of machine learning. The multiple hidden layer exponential logistic regression model (also known as MELM) proposed in this study retains the properties of the parameters of the first hidden layer. A system that approaches the expected hidden layer output with the real output zero error can be constructed in order to determine the parameters of the remaining hidden layers. Extensive studies on the MELM algorithm for regression and classification demonstrate that, in comparison to other multilayer ELMs, the ELM, and two-hidden-layer ELM (TELM), it may yield the intended outcomes based on average precision and strong generalisation performance. This research will function as a point of reference for scholars and experts in the industry. Additionally, from a technological perspective, it will provide a standard for decision-makers across many application domains and real-world situations.

Downloads

Download data is not yet available.

References

Injadat, M., Moubayed, A., Nassif, A. B., & Shami, A. (2021). Machine learning towards intelligent systems: applications, challenges, and opportunities. Artificial Intelligence Review, 54, 3299-3348.

Ertuğrul, Ö. F., & Kaya, Y. (2014). A detailed analysis on extreme learning machine and novel approaches based on ELM. American Journal of computer science and engineering, 1(5), 43-50.

Wang, J., Cai, L., Peng, J., & Jia, Y. (2015). A novel multiple instance learning method based on extreme learning machine. Computational Intelligence and Neuroscience, 2015, 3-3.

Jhaveri, R. H., Revathi, A., Ramana, K., Raut, R., & Dhanaraj, R. K. (2022). A review on machine learning strategies for real-world engineering applications. Mobile Information Systems, 2022.

Wang, J., Lu, S., Wang, S. H., & Zhang, Y. D. (2022). A review on extreme learning machine. Multimedia Tools and Applications, 81(29), 41611-41660.

Ding, S., Xu, X., & Nie, R. (2014). Extreme learning machine and its applications. Neural Computing and Applications, 25, 549-556.

Zhang, J., Ding, S., Zhang, N., & Shi, Z. (2016). Incremental extreme learning machine based on deep feature embedded. International Journal of Machine Learning and Cybernetics, 7, 111-120.

Huang, G. B. (2015). What are extreme learning machines? Filling the gap between Frank Rosenblatt’s dream and John von Neumann’s puzzle. Cognitive Computation, 7, 263-278.

Zhang, J., Li, Y., Xiao, W., & Zhang, Z. (2020). Non-iterative and fast deep learning: Multilayer extreme learning machines. Journal of the Franklin Institute, 357(13), 8925-8955.

de Campos Souza, P. V., Araujo, V. S., Guimaraes, A. J., Araujo, V. J. S., & Rezende, T. S. (2018, November). Method of pruning the hidden layer of the extreme learning machine based on correlation coefficient. In 2018 IEEE Latin American conference on computational intelligence (LA-CCI) (pp. 1-6). IEEE.

Xiao, D., Li, B., & Mao, Y. (2017). A multiple hidden layers extreme learning machine method and its application. Mathematical Problems in Engineering, 2017.

Liu, J., & Le, B. T. (2019). Incremental Multiple Hidden Layers Regularized Extreme Learning Machine Based on Forced Positive-Definite Cholesky Factorization. Mathematical Problems in Engineering, 2019.

Rodrigues, I. R., Neto, S. R. D. S., Kelner, J., Sadok, D., & Endo, P. T. Convolutional extreme learning machines: a systematic review. Informatics 8 (2), 33 (2021).

Ding, S., Zhao, H., Zhang, Y., Xu, X., & Nie, R. (2015). Extreme learning machine: algorithm, theory and applications. Artificial Intelligence Review, 44, 103-115.

Downloads

Published

27.12.2023

How to Cite

Kumar, M. ., Kumar, G. K. ., Ali, A. M. ., Kanna, S. R. ., & Lakshmi, K. M. . (2023). Analysis of Extreme Learning Machine Based on Multiple Hidden Layers. International Journal of Intelligent Systems and Applications in Engineering, 12(9s), 96–103. Retrieved from https://ijisae.org/index.php/IJISAE/article/view/4208

Issue

Vol. 12 No. 9s (2024)

Section

Research Article

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.

IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.