Modified symbiotic organisms search optimization for automatic construction of convolutional neural network architectures
Convolutional Neural Networks (ConvNets) have demonstrated impressive capabilities in image classification; however, the manual creation of these models is a labor-intensive and time-consuming endeavor due to their inherent complexity. This research introduces an innovative approach to Convolution...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/112662/2/112662_Modified%20symbiotic%20organisms%20search%20optimization.pdf http://irep.iium.edu.my/112662/3/112662_Modified%20symbiotic%20organisms%20search%20optimization_Scopus.pdf http://irep.iium.edu.my/112662/ https://www.sciencedirect.com/journal/intelligent-systems-with-applications/vol/22/suppl/C https://doi.org/10.1016/j.iswa.2024.200349 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Universiti Islam Antarabangsa Malaysia |
| Language: | English English |
| Summary: | Convolutional Neural Networks (ConvNets) have demonstrated impressive capabilities in image classification;
however, the manual creation of these models is a labor-intensive and time-consuming endeavor due to their
inherent complexity. This research introduces an innovative approach to Convolutional Neural Network (ConvNet) architecture generation through the utilization of the Symbiotic Organism Search ConvNet (SOS_ConvNet)
algorithm. Leveraging the Symbiotic Organism Search optimization technique, SOS_ConvNet evolves ConvNet
architectures tailored for diverse image classification tasks. The algorithm’s distinctive feature lies in its ability to
perform non-numeric computations, rendering it adaptable to intricate deep learning problems. To assess the
effectiveness of SOS_ConvNet, experiments were conducted on diverse datasets, including MNIST, FashionMNIST, CIFAR-10, and the Breast Cancer dataset. Comparative analysis against existing models showcased the
superior performance of SOS_ConvNet in terms of accuracy, error rate, and parameter efficiency. Notably, on the
MNIST dataset, SOS_ConvNet achieved an impressive 0.31 % error rate, while on Fashion-MNIST, it demonstrated a competitive 6.7 % error rate, coupled with unparalleled parameter efficiency of 0.24 million parameters. The model excelled on CIFAR-10 and BreakHis datasets, yielding accuracies of 82.78 % and 89.12 %,
respectively. Remarkably, the algorithm achieves remarkable accuracy while maintaining moderate model size. |
|---|