This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
Improving the Generalization Abilities of Constructed Neural Networks with the Addition of Local Optimization Techniques
by
Ioannis G. Tsoulos
Ioannis G. Tsoulos 1,*,
Vasileios Charilogis
Vasileios Charilogis 1,
Dimitrios Tsalikakis
Dimitrios Tsalikakis 2 and
Alexandros Tzallas
Alexandros Tzallas 1
1
Department of Informatics and Telecommunications, University of Ioannina, 45110 Ioannina, Greece
2
Department of Engineering Informatics and Telecommunications, University of Western Macedonia, 50100 Kozani, Greece
*
Author to whom correspondence should be addressed.
Algorithms 2024, 17(10), 446; https://doi.org/10.3390/a17100446 (registering DOI)
Submission received: 12 September 2024
/
Revised: 29 September 2024
/
Accepted: 4 October 2024
/
Published: 6 October 2024
Abstract
Constructed neural networks with the assistance of grammatical evolution have been widely used in a series of classification and data-fitting problems recently. Application areas of this innovative machine learning technique include solving differential equations, autism screening, and measuring motor function in Parkinson’s disease. Although this technique has given excellent results, in many cases, it is trapped in local minimum and cannot perform satisfactorily in many problems. For this purpose, it is considered necessary to find techniques to avoid local minima, and one technique is the periodic application of local minimization techniques that will adjust the parameters of the constructed artificial neural network while maintaining the already existing architecture created by grammatical evolution. The periodic application of local minimization techniques has shown a significant reduction in both classification and data-fitting problems found in the relevant literature.
Share and Cite
MDPI and ACS Style
Tsoulos, I.G.; Charilogis, V.; Tsalikakis, D.; Tzallas, A.
Improving the Generalization Abilities of Constructed Neural Networks with the Addition of Local Optimization Techniques. Algorithms 2024, 17, 446.
https://doi.org/10.3390/a17100446
AMA Style
Tsoulos IG, Charilogis V, Tsalikakis D, Tzallas A.
Improving the Generalization Abilities of Constructed Neural Networks with the Addition of Local Optimization Techniques. Algorithms. 2024; 17(10):446.
https://doi.org/10.3390/a17100446
Chicago/Turabian Style
Tsoulos, Ioannis G., Vasileios Charilogis, Dimitrios Tsalikakis, and Alexandros Tzallas.
2024. "Improving the Generalization Abilities of Constructed Neural Networks with the Addition of Local Optimization Techniques" Algorithms 17, no. 10: 446.
https://doi.org/10.3390/a17100446
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article metric data becomes available approximately 24 hours after publication online.