Imagen de Portada

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

Guardado en:
Publicado en:Mathematics vol. 13, no. 4 (2025), p. 605
Autor principal: Franco-Gaona, Erick
Otros Autores: Avila-Garcia, Maria Susana, Cruz-Aceves, Ivan
Publicado:
MDPI AG
Materias:
Marginal Distribution
Machine learning
Artificial intelligence
Image databases
Databases
Optimization techniques
Artificial neural networks
Genetic algorithms
Neural networks
Searching
Classification
Image classification
Algorithms
Methods
Automation
Computing time
Heuristic methods
Acceso en línea:Citation/Abstract
Full Text + Graphics
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Resumen: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.
ISSN:2227-7390
DOI:10.3390/math13040605
Fuente:Engineering Database