Back to Search Start Over

MTLBORKS-CNN: An Innovative Approach for Automated Convolutional Neural Network Design for Image Classification

Authors :
Koon Meng Ang
Wei Hong Lim
Sew Sun Tiang
Abhishek Sharma
S. K. Towfek
Abdelaziz A. Abdelhamid
Amal H. Alharbi
Doaa Sami Khafaga
Source :
Mathematics, Vol 11, Iss 19, p 4115 (2023)
Publication Year :
2023
Publisher :
MDPI AG, 2023.

Abstract

Convolutional neural networks (CNNs) have excelled in artificial intelligence, particularly in image-related tasks such as classification and object recognition. However, manually designing CNN architectures demands significant domain expertise and involves time-consuming trial-and-error processes, along with substantial computational resources. To overcome this challenge, an automated network design method known as Modified Teaching-Learning-Based Optimization with Refined Knowledge Sharing (MTLBORKS-CNN) is introduced. It autonomously searches for optimal CNN architectures, achieving high classification performance on specific datasets without human intervention. MTLBORKS-CNN incorporates four key features. It employs an effective encoding scheme for various network hyperparameters, facilitating the search for innovative and valid network architectures. During the modified teacher phase, it leverages a social learning concept to calculate unique exemplars that effectively guide learners while preserving diversity. In the modified learner phase, self-learning and adaptive peer learning are incorporated to enhance knowledge acquisition of learners during CNN architecture optimization. Finally, MTLBORKS-CNN employs a dual-criterion selection scheme, considering both fitness and diversity, to determine the survival of learners in subsequent generations. MTLBORKS-CNN is rigorously evaluated across nine image datasets and compared with state-of-the-art methods. The results consistently demonstrate MTLBORKS-CNN’s superiority in terms of classification accuracy and network complexity, suggesting its potential for infrastructural development of smart devices.

Details

Language :
English
ISSN :
22277390
Volume :
11
Issue :
19
Database :
Directory of Open Access Journals
Journal :
Mathematics
Publication Type :
Academic Journal
Accession number :
edsdoj.27b214529ad84708ae0bbb513d23286f
Document Type :
article
Full Text :
https://doi.org/10.3390/math11194115