Faculty, Staff and Student Publications
Publication Date
9-9-2022
Journal
Patterns
Abstract
Convolutional neural networks (CNNs) are deep learning models used widely for solving various tasks like computer vision and speech recognition. CNNs are developed manually based on problem-specific domain knowledge and tricky settings, which are laborious, time consuming, and challenging. To solve these, our study develops an improved differential evolution of convolutional neural network (IDECNN) algorithm to design CNN layer architectures for image classification. Variable-length encoding is utilized to represent the flexible layer architecture of a CNN model in IDECNN. An efficient heuristic mechanism is proposed in IDECNN to evolve CNN architecture through mutation and crossover to prevent premature convergence during the evolutionary process. Eight well-known imaging datasets were utilized. The results showed that IDECNN could design suitable architecture compared with 20 existing CNN models. Finally, CNN architectures are applied to pneumonia and coronavirus disease 2019 (COVID-19) X-ray biomedical image data. The results demonstrated the usefulness of the proposed approach to generate a suitable CNN model.
Keywords
neural architecture search, NAS, convolutional neural network, CNN, differential evolution, DE, image classification, neuroevolution, optimal neural architecture
DOI
10.1016/j.patter.2022.100567
PMID
36124301
PMCID
PMC9481963
PubMedCentral® Posted Date
8-24-2022
PubMedCentral® Full Text Version
Post-print
Published Open-Access
yes
Graphical Abstract