Your browser doesn't support javascript.
Designing optimal convolutional neural network architecture using differential evolution algorithm.
Ghosh, Arjun; Jana, Nanda Dulal; Mallik, Saurav; Zhao, Zhongming.
  • Ghosh A; Department of Computer Science and Engineering, National Institute of Technology Durgapur, Durgapur, West Bengal 713209, India.
  • Jana ND; Department of Computer Science and Engineering, National Institute of Technology Durgapur, Durgapur, West Bengal 713209, India.
  • Mallik S; Center for Precision Health, School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX 77030, USA.
  • Zhao Z; Molecular and Integrative Physiological Sciences, Department of Environmental Health, Harvard T. H. Chan School of Public Health, Boston, MA 02115, USA.
Patterns (N Y) ; 3(9): 100567, 2022 Sep 09.
Article in English | MEDLINE | ID: covidwho-1996475
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

Full text: Available Collection: International databases Database: MEDLINE Language: English Journal: Patterns (N Y) Year: 2022 Document Type: Article Affiliation country: J.patter.2022.100567

Similar

MEDLINE

...
LILACS

LIS


Full text: Available Collection: International databases Database: MEDLINE Language: English Journal: Patterns (N Y) Year: 2022 Document Type: Article Affiliation country: J.patter.2022.100567