Fully automatic CNN design with inception and ResNet blocks


Barakbayeva T., Demirci F. M.

Neural Computing and Applications, vol.35, no.2, pp.1569-1580, 2023 (SCI-Expanded) identifier identifier

  • Publication Type: Article / Article
  • Volume: 35 Issue: 2
  • Publication Date: 2023
  • Doi Number: 10.1007/s00521-022-07700-9
  • Journal Name: Neural Computing and Applications
  • Journal Indexes: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, PASCAL, Applied Science & Technology Source, Biotechnology Research Abstracts, Compendex, Computer & Applied Sciences, Index Islamicus, INSPEC, zbMATH
  • Page Numbers: pp.1569-1580
  • Keywords: Convolutional neural networks, Genetic algorithms, Automatic CNN construction
  • Ankara Yıldırım Beyazıt University Affiliated: Yes

Abstract

© 2022, The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature.Although convolutional neural networks (CNNs) are widely used in image classification tasks and have demonstrated promising classification accuracy results, designing a CNN architecture requires a manual adjustment of parameters through a series of experiments as well as sufficient knowledge both in the problem domain and CNN architecture design. Therefore, it is difficult for users without prior experience to design a CNN for specific purposes. In this paper, we propose a framework for the automatic construction of CNN architectures based on ResNet, DenseNet, and Inception blocks and the roulette wheel selection method with a dynamic learning rate. Compared with the state of the art, the proposed approach has a significant improvement in the domain of image classification. Experimental evaluation of our approach including a comparison with the previous works on three benchmark datasets demonstrates the effectiveness of the overall method. The proposed algorithm not only improves the previous algorithm but also keeps the advantages of automatic CNN construction without requiring manual interventions. The source code of the our framework can be found at https://github.com/btogzhan2000/ea-cnn-complab.