Fully automatic CNN design with inception and ResNet blocks

• Published in: Neural computing & applications Vol. 35; no. 2; pp. 1569 - 1580
• Main Authors: Barakbayeva, Togzhan, Demirci, Fatih M.
• Format: Journal Article
• Language: English
• Published: London Springer London 2023; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Artificial neural networks; Classification; Computational Biology/Bioinformatics; Computational Science and Engineering; Computer engineering; Computer Science; Data Mining and Knowledge Discovery; Design; Domains; Genetic algorithms; Image classification; Image Processing and Computer Vision; Methods; Mutation; Neural networks; Original Article; Probability and Statistics in Computer Science; Source code; Convolutional neural networks; Automatic CNN construction; Genetic algorithms
• ISSN: 0941-0643; 1433-3058
• DOI: 10.1007/s00521-022-07700-9

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 .