Next Article in Journal
A Systematic Review of Design Workshops for Health Information Technologies
Previous Article in Journal
Factors Affecting the Use of Smart Mobile Examination Platforms by Universities’ Postgraduate Students during the COVID-19 Pandemic: An Empirical Study
Previous Article in Special Issue
Feasibility Study on the Role of Personality, Emotion, and Engagement in Socially Assistive Robotics: A Cognitive Assessment Scenario
Article

Convolutional Extreme Learning Machines: A Systematic Review

1
Centro de Informática, Universidade Federal de Pernambuco (UFPE), Recife 50670-420, Brazil
2
Programa de Pós-Graduação em Engenharia da Computação, Universidade de Pernambuco (UPE), Recife 50050-000, Brazil
*
Authors to whom correspondence should be addressed.
Academic Editor: Antony Bryant
Received: 1 April 2021 / Revised: 4 May 2021 / Accepted: 5 May 2021 / Published: 13 May 2021
(This article belongs to the Special Issue Feature Paper in Informatics)
Much work has recently identified the need to combine deep learning with extreme learning in order to strike a performance balance with accuracy, especially in the domain of multimedia applications. When considering this new paradigm—namely, the convolutional extreme learning machine (CELM)—we present a systematic review that investigates alternative deep learning architectures that use the extreme learning machine (ELM) for faster training to solve problems that are based on image analysis. We detail each of the architectures that are found in the literature along with their application scenarios, benchmark datasets, main results, and advantages, and then present the open challenges for CELM. We followed a well-structured methodology and established relevant research questions that guided our findings. Based on 81 primary studies, we found that object recognition is the most common problem that is solved by CELM, and CCN with predefined kernels is the most common CELM architecture proposed in the literature. The results from experiments show that CELM models present good precision, convergence, and computational performance, and they are able to decrease the total processing time that is required by the learning process. The results presented in this systematic review are expected to contribute to the research area of CELM, providing a good starting point for dealing with some of the current problems in the analysis of computer vision based on images. View Full-Text
Keywords: convolutional extreme learning machine; deep learning; multimedia analysis convolutional extreme learning machine; deep learning; multimedia analysis
Show Figures

Figure 1

MDPI and ACS Style

Rodrigues, I.R.; da Silva Neto, S.R.; Kelner, J.; Sadok, D.; Endo, P.T. Convolutional Extreme Learning Machines: A Systematic Review. Informatics 2021, 8, 33. https://0-doi-org.brum.beds.ac.uk/10.3390/informatics8020033

AMA Style

Rodrigues IR, da Silva Neto SR, Kelner J, Sadok D, Endo PT. Convolutional Extreme Learning Machines: A Systematic Review. Informatics. 2021; 8(2):33. https://0-doi-org.brum.beds.ac.uk/10.3390/informatics8020033

Chicago/Turabian Style

Rodrigues, Iago R.; da Silva Neto, Sebastião R.; Kelner, Judith; Sadok, Djamel; Endo, Patricia T. 2021. "Convolutional Extreme Learning Machines: A Systematic Review" Informatics 8, no. 2: 33. https://0-doi-org.brum.beds.ac.uk/10.3390/informatics8020033

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop