Evolutionary Computation Paradigm to Determine Deep Neural Networks Architectures

International Journal of Computers Communications & Control

article

Renato Constantin Ivanescu¹  Smaranda Belciug²  Andrei Nascu²  Mircea Sebastian Serbanescu³  Dominic Gabriel Iliescu³ 

[1] University of Craiova, Department of Computers and Information Technologies;University of Craiova, Department of Computer Science;University of Craiova, Romania and University of Medicine and Pharmacy of Craiova

关键词: Deep Learning;    evolutionary computation;    Statistical Analysis;    fetal morphology;    image classification;   

DOI  :  10.15837/ijccc.2022.5.4886

学科分类：自动化工程

来源: Universitatea Agora

【 摘 要 】

Image classification is usually done using deep learning algorithms. Deep learning architectures are set deterministically. The aim of this paper is to propose an evolutionary computation paradigm that optimises a deep learning neural network’s architecture. A set of chromosomes are randomly generated, after which selection, recombination, and mutation are applied. At each generation the fittest chromosomes are kept. The best chromosome from the last generation determines the deep learning architecture. We have tested our method on a second trimester fetal morphology database. The proposed model is statistically compared with DenseNet201 and ResNet50, proving its competitiveness.

【 授权许可】

CC BY-NC