Performance of a Novel Chaotic Firefly Algorithm with Enhanced Exploration for Tackling Global Optimization Problems: Application for Dropout Regularization

Swarm intelligence techniques have been created to respond to theoretical and practical global optimization problems. This paper puts forward an enhanced version of the firefly algorithm that corrects the acknowledged drawbacks of the original method, by an explicit exploration mechanism and a chaot...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Mathematics (Basel) Jg. 9; H. 21; S. 2705
Hauptverfasser: Bacanin, Nebojsa, Stoean, Ruxandra, Zivkovic, Miodrag, Petrovic, Aleksandar, Rashid, Tarik A., Bezdan, Timea
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Basel MDPI AG 01.11.2021
Schlagworte:
Algorithms
Animals
Artificial intelligence
Artificial neural networks
Behavior
Benchmarks
convolutional neural networks
Deep learning
dropout
Global optimization
Heuristic methods
Image processing
Machine learning
metaheuristics
Neural networks
Optimization
Regularization
Statistical tests
Swarm intelligence
ISSN:2227-7390, 2227-7390
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Swarm intelligence techniques have been created to respond to theoretical and practical global optimization problems. This paper puts forward an enhanced version of the firefly algorithm that corrects the acknowledged drawbacks of the original method, by an explicit exploration mechanism and a chaotic local search strategy. The resulting augmented approach was theoretically tested on two sets of bound-constrained benchmark functions from the CEC suites and practically validated for automatically selecting the optimal dropout rate for the regularization of deep neural networks. Despite their successful applications in a wide spectrum of different fields, one important problem that deep learning algorithms face is overfitting. The traditional way of preventing overfitting is to apply regularization; the first option in this sense is the choice of an adequate value for the dropout parameter. In order to demonstrate its ability in finding an optimal dropout rate, the boosted version of the firefly algorithm has been validated for the deep learning subfield of convolutional neural networks, with respect to five standard benchmark datasets for image processing: MNIST, Fashion-MNIST, Semeion, USPS and CIFAR-10. The performance of the proposed approach in both types of experiments was compared with other recent state-of-the-art methods. To prove that there are significant improvements in results, statistical tests were conducted. Based on the experimental data, it can be concluded that the proposed algorithm clearly outperforms other approaches.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2227-7390
2227-7390
DOI:10.3390/math9212705