Full text

Turn on search term navigation

© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.

Abstract

This work proposes the use of a micro genetic algorithm to optimize the architecture of fully connected layers in convolutional neural networks, with the aim of reducing model complexity without sacrificing performance. Our approach applies the paradigm of transfer learning, enabling training without the need for extensive datasets. A micro genetic algorithm requires fewer computational resources due to its reduced population size, while still preserving a substantial degree of the search capabilities found in algorithms with larger populations. By exploring different representations and objective functions, including classification accuracy, hidden neuron ratio, minimum redundancy, and maximum relevance for feature selection, eight algorithmic variants were developed, with six variants performing both hidden layers reduction and feature-selection tasks. Experimental results indicate that the proposed algorithm effectively reduces the architecture of the fully connected layers in the convolutional neural network. The variant achieving the best reduction used only 44% of the convolutional features in the input layer, and only 9.7% of neurons in the hidden layers, without negatively impacting (statistically confirmed) classification accuracy when compared to a network model based on a full reference architecture and a representative method from the literature.

Details

Title
Optimization of Deep Neural Networks Using a Micro Genetic Algorithm
Author
Landa, Ricardo 1   VIAFID ORCID Logo  ; Tovias-Alanis, David 1 ; Toscano, Gregorio 2   VIAFID ORCID Logo 

 Tamaulipas Campus, Cinvestav, Cd. Victoria 87130, Mexico; [email protected] 
 Department of Electrical Engineering and Computer Science, The Catholic University of America, Washington, DC 20064, USA; [email protected] 
First page
2651
Publication year
2024
Publication date
2024
Publisher
MDPI AG
e-ISSN
26732688
Source type
Scholarly Journal
Language of publication
English
ProQuest document ID
3149498890
Copyright
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.