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 Convolutional...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-06-01
|
| Series: | Intelligent Systems with Applications |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667305324000255 |
| _version_ | 1827222858114269184 |
|---|---|
| author | Fatsuma Jauro Abdulsalam Ya'u Gital Usman Ali Abdullahi Aminu Onimisi Abdulsalami Mohammed Abdullahi Adamu Abubakar Ibrahim Haruna Chiroma |
| author_facet | Fatsuma Jauro Abdulsalam Ya'u Gital Usman Ali Abdullahi Aminu Onimisi Abdulsalami Mohammed Abdullahi Adamu Abubakar Ibrahim Haruna Chiroma |
| author_sort | Fatsuma Jauro |
| collection | DOAJ |
| description | 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, Fashion-MNIST, 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. |
| first_indexed | 2024-04-24T23:23:11Z |
| format | Article |
| id | doaj.art-d15227aba8d846f595baa8ee8e0416a8 |
| institution | Directory Open Access Journal |
| issn | 2667-3053 |
| language | English |
| last_indexed | 2025-03-21T16:45:10Z |
| publishDate | 2024-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Intelligent Systems with Applications |
| spelling | doaj.art-d15227aba8d846f595baa8ee8e0416a82024-06-16T05:48:18ZengElsevierIntelligent Systems with Applications2667-30532024-06-0122200349Modified symbiotic organisms search optimization for automatic construction of convolutional neural network architecturesFatsuma Jauro0Abdulsalam Ya'u Gital1Usman Ali Abdullahi2Aminu Onimisi Abdulsalami3Mohammed Abdullahi4Adamu Abubakar Ibrahim5Haruna Chiroma6Department of Computer Science, Ahmadu Bello University, Zaria, Nigeria; Department of Mathematical Science, Abubakar Tafawa Balewa University Bauchi, Nigeria; Corresponding author.Department of Mathematical Science, Abubakar Tafawa Balewa University Bauchi, NigeriaDepartment of Computer Science, Federal College of Education, Technical, Gombe, TanzaniaDepartment of Computer Science, Ahmadu Bello University, Zaria, Nigeria; School of Computer Science and Artificial Intelligence, Wuhan University of Technology, PR ChinaDepartment of Computer Science, Ahmadu Bello University, Zaria, NigeriaDepartment of Computer Science, International Islamic University, MalaysiaCollege of Computer Science and Engineering, University of Hafr Al Batin, Saudi Arabia; Corresponding author.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, Fashion-MNIST, 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.http://www.sciencedirect.com/science/article/pii/S2667305324000255Convolutional neural networkNeural architecture searchSymbiotic organism searchAnd deep learning |
| spellingShingle | Fatsuma Jauro Abdulsalam Ya'u Gital Usman Ali Abdullahi Aminu Onimisi Abdulsalami Mohammed Abdullahi Adamu Abubakar Ibrahim Haruna Chiroma Modified symbiotic organisms search optimization for automatic construction of convolutional neural network architectures Intelligent Systems with Applications Convolutional neural network Neural architecture search Symbiotic organism search And deep learning |
| title | Modified symbiotic organisms search optimization for automatic construction of convolutional neural network architectures |
| title_full | Modified symbiotic organisms search optimization for automatic construction of convolutional neural network architectures |
| title_fullStr | Modified symbiotic organisms search optimization for automatic construction of convolutional neural network architectures |
| title_full_unstemmed | Modified symbiotic organisms search optimization for automatic construction of convolutional neural network architectures |
| title_short | Modified symbiotic organisms search optimization for automatic construction of convolutional neural network architectures |
| title_sort | modified symbiotic organisms search optimization for automatic construction of convolutional neural network architectures |
| topic | Convolutional neural network Neural architecture search Symbiotic organism search And deep learning |
| url | http://www.sciencedirect.com/science/article/pii/S2667305324000255 |
| work_keys_str_mv | AT fatsumajauro modifiedsymbioticorganismssearchoptimizationforautomaticconstructionofconvolutionalneuralnetworkarchitectures AT abdulsalamyaugital modifiedsymbioticorganismssearchoptimizationforautomaticconstructionofconvolutionalneuralnetworkarchitectures AT usmanaliabdullahi modifiedsymbioticorganismssearchoptimizationforautomaticconstructionofconvolutionalneuralnetworkarchitectures AT aminuonimisiabdulsalami modifiedsymbioticorganismssearchoptimizationforautomaticconstructionofconvolutionalneuralnetworkarchitectures AT mohammedabdullahi modifiedsymbioticorganismssearchoptimizationforautomaticconstructionofconvolutionalneuralnetworkarchitectures AT adamuabubakaribrahim modifiedsymbioticorganismssearchoptimizationforautomaticconstructionofconvolutionalneuralnetworkarchitectures AT harunachiroma modifiedsymbioticorganismssearchoptimizationforautomaticconstructionofconvolutionalneuralnetworkarchitectures |