2022
DOI: 10.32604/cmc.2022.020449
|View full text |Cite
|
Sign up to set email alerts
|

Training Multi-Layer Perceptron with Enhanced Brain Storm Optimization Metaheuristics

Abstract: In the domain of artificial neural networks, the learning process represents one of the most challenging tasks. Since the classification accuracy highly depends on the weights and biases, it is crucial to find its optimal or suboptimal values for the problem at hand. However, to a very large search space, it is very difficult to find the proper values of connection weights and biases. Employing traditional optimization algorithms for this issue leads to slow convergence and it is prone to get stuck in the loca… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
10
0

Year Published

2022
2022
2023
2023

Publication Types

Select...
6
4

Relationship

4
6

Authors

Journals

citations
Cited by 43 publications
(10 citation statements)
references
References 29 publications
0
10
0
Order By: Relevance
“…Other successful applications of metaheuristics optimizers include tuning of the cloud, edge and fog computing [2,5,15,23,46,59], feature selection challenge [8,19,22,32,37,49,61], dropout regularization [11], a variety of COVID-19 applications [25,58,[62][63][64], tuning artificial neural networks [3,6,7,10,13,18,44], text clustering [21,50] and cryptocurrency price forecast [42].…”
Section: Metaheuristics Optimizationmentioning
confidence: 99%
“…Other successful applications of metaheuristics optimizers include tuning of the cloud, edge and fog computing [2,5,15,23,46,59], feature selection challenge [8,19,22,32,37,49,61], dropout regularization [11], a variety of COVID-19 applications [25,58,[62][63][64], tuning artificial neural networks [3,6,7,10,13,18,44], text clustering [21,50] and cryptocurrency price forecast [42].…”
Section: Metaheuristics Optimizationmentioning
confidence: 99%
“…This family of metaheuristic approaches has been extensively utilized to address numerous practical real-world problems with NP-hard complexity from the domain of heterogeneous real-world domains. Some notable examples of this kind of applications include cloud-edge computing and task scheduling [30,31], wireless sensors networks (WSNs) challenges such as node localization and prolonging the overall lifetime of the network [32,33], healthcare applications and pollution estimation [34], ANNs challenges including feature selection and hyperparameters' optimization tasks [3,[35][36][37][38], cryptocurrency trends estimations [39], computer-guided illness detection [40][41][42], and lastly the occurring COVID-19 global epidemic-associated applications [43][44][45][46].…”
Section: Swarm Intelligencementioning
confidence: 99%
“…The algorithms from this group have been used in a wide spectrum of different challenges with NP-hardness from the computer science field. These applications include the problem of global numerical optimization [37], scheduling of tasks in the cloud-edge environments [38][39][40], health care systems and pollution prediction [41], the problems of wireless sensors networks including localization and lifetime maximization [42][43][44], artificial neural networks optimization [45][46][47][48][49][50][51][52][53][54][55][56][57], feature selection in general [58,59], text document clustering [48], cryptocurrency values prediction [60], computer-aided medical diagnostics [61][62][63][64], and, finally, the ongoing COVID-19 pandemic related applications [65][66][67].…”
Section: Swarm Intelligencementioning
confidence: 99%