Automatic Neural Architecture Search Based on an Estimation of Distribution Algorithm for Binary Classification of Image Databases

Saved in:
Bibliographic Details
Published in:Mathematics vol. 13, no. 4 (2025), p. 605
Main Author: Franco-Gaona, Erick
Other Authors: Avila-Garcia, Maria Susana, Cruz-Aceves, Ivan
Published:
MDPI AG
Subjects:
Online Access:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Tags: Add Tag
No Tags, Be the first to tag this record!

MARC

LEADER 00000nab a2200000uu 4500
001 3171096724
003 UK-CbPIL
022 |a 2227-7390 
024 7 |a 10.3390/math13040605  |2 doi 
035 |a 3171096724 
045 2 |b d20250101  |b d20251231 
084 |a 231533  |2 nlm 
100 1 |a Franco-Gaona, Erick  |u Departamento de Estudios Multidisciplinarios, División de Ingenierías, Campus Irapuato-Salamanca Universidad de Guanajuato, Av. Universidad S/N, Yuriria 38944, Guanajuato, Mexico; <email>e.francogaona@ugto.mx</email> (E.F.-G.); <email>susana.avila@ugto.mx</email> (M.S.A.-G.) 
245 1 |a Automatic Neural Architecture Search Based on an Estimation of Distribution Algorithm for Binary Classification of Image Databases 
260 |b MDPI AG  |c 2025 
513 |a Journal Article 
520 3 |a Convolutional neural networks (CNNs) are widely used for image classification; however, setting the appropriate hyperparameters before training is subjective and time consuming, and the search space is not properly explored. This paper presents a novel method for the automatic neural architecture search based on an estimation of distribution algorithm (EDA) for binary classification problems. The hyperparameters were coded in binary form due to the nature of the metaheuristics used in the automatic search stage of CNN architectures which was performed using the Boltzmann Univariate Marginal Distribution algorithm (BUMDA) chosen by statistical comparison between four metaheuristics to explore the search space, whose computational complexity is O(<inline-formula>229</inline-formula>). Moreover, the proposed method is compared with multiple state-of-the-art methods on five databases, testing its efficiency in terms of accuracy and F1-score. In the experimental results, the proposed method achieved an F1-score of 97.2%, 98.73%, 97.23%, 98.36%, and 98.7% in its best evaluation, better results than the literature. Finally, the computational time of the proposed method for the test set was ≈0.6 s, 1 s, 0.7 s, 0.5 s, and 0.1 s, respectively. 
610 4 |a Marginal Distribution 
653 |a Machine learning 
653 |a Artificial intelligence 
653 |a Image databases 
653 |a Databases 
653 |a Optimization techniques 
653 |a Artificial neural networks 
653 |a Genetic algorithms 
653 |a Neural networks 
653 |a Searching 
653 |a Classification 
653 |a Image classification 
653 |a Algorithms 
653 |a Methods 
653 |a Automation 
653 |a Computing time 
653 |a Heuristic methods 
700 1 |a Avila-Garcia, Maria Susana  |u Departamento de Estudios Multidisciplinarios, División de Ingenierías, Campus Irapuato-Salamanca Universidad de Guanajuato, Av. Universidad S/N, Yuriria 38944, Guanajuato, Mexico; &lt;email&gt;e.francogaona@ugto.mx&lt;/email&gt; (E.F.-G.); &lt;email&gt;susana.avila@ugto.mx&lt;/email&gt; (M.S.A.-G.) 
700 1 |a Cruz-Aceves, Ivan  |u SECIHTI-Centro de investigación en Matemáticas (CIMAT), Valenciana 36023, Guanajuato, Mexico 
773 0 |t Mathematics  |g vol. 13, no. 4 (2025), p. 605 
786 0 |d ProQuest  |t Engineering Database 
856 4 1 |3 Citation/Abstract  |u https://www.proquest.com/docview/3171096724/abstract/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text + Graphics  |u https://www.proquest.com/docview/3171096724/fulltextwithgraphics/embedded/L8HZQI7Z43R0LA5T?source=fedsrch 
856 4 0 |3 Full Text - PDF  |u https://www.proquest.com/docview/3171096724/fulltextPDF/embedded/L8HZQI7Z43R0LA5T?source=fedsrch