Eliminating Network Depth: Genetic Algorithm for Parameter Optimization in CNNs
Recent advances in Convolutional Neural Networks (CNNs) have significantly enhanced image classification performance. However, CNNs often require large numbers of parameters, leading to increased computational complexity, prolonged training times, and substantial resource demands. Achieving higher c...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10852290/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825207053850771456 |
|---|---|
| author | M. Askari S. Soleimani M. H. Shakoor M. Momeni |
| author_facet | M. Askari S. Soleimani M. H. Shakoor M. Momeni |
| author_sort | M. Askari |
| collection | DOAJ |
| description | Recent advances in Convolutional Neural Networks (CNNs) have significantly enhanced image classification performance. However, CNNs often require large numbers of parameters, leading to increased computational complexity, prolonged training times, and substantial resource demands. Achieving higher classification accuracy typically involves deepening network architectures, which further exacerbates these challenges. This paper proposes a novel method based on a genetic algorithm to optimize parameter selection, enabling the construction of CNNs that achieve superior accuracy with fewer parameters. By focusing on parameters with the most significant impact on performance, the method reduces the need for deeper networks, thereby minimizing computational costs. Experimental results demonstrate that the proposed algorithm outperforms its counterparts. For instance, the generated CNN achieves an accuracy improvement of 0.75 percentage points over ResNet-110 while using 84% fewer parameters. These findings highlight the method’s potential to balance efficiency and accuracy, making it a promising solution for resource-constrained applications. |
| format | Article |
| id | doaj-art-d0417d277b7049d380e7d269016e8065 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-d0417d277b7049d380e7d269016e80652025-02-07T00:01:33ZengIEEEIEEE Access2169-35362025-01-0113224732248810.1109/ACCESS.2025.353397610852290Eliminating Network Depth: Genetic Algorithm for Parameter Optimization in CNNsM. Askari0https://orcid.org/0000-0001-7284-5908S. Soleimani1M. H. Shakoor2https://orcid.org/0000-0001-8672-5181M. Momeni3Department of Computer Engineering, Faculty of Engineering, Arak University, Arak, IranDepartment of Computer Engineering, Faculty of Engineering, Arak University, Arak, IranDepartment of Computer Engineering, Faculty of Engineering, Arak University, Arak, IranDepartment of Computer Engineering, Faculty of Engineering, Arak University, Arak, IranRecent advances in Convolutional Neural Networks (CNNs) have significantly enhanced image classification performance. However, CNNs often require large numbers of parameters, leading to increased computational complexity, prolonged training times, and substantial resource demands. Achieving higher classification accuracy typically involves deepening network architectures, which further exacerbates these challenges. This paper proposes a novel method based on a genetic algorithm to optimize parameter selection, enabling the construction of CNNs that achieve superior accuracy with fewer parameters. By focusing on parameters with the most significant impact on performance, the method reduces the need for deeper networks, thereby minimizing computational costs. Experimental results demonstrate that the proposed algorithm outperforms its counterparts. For instance, the generated CNN achieves an accuracy improvement of 0.75 percentage points over ResNet-110 while using 84% fewer parameters. These findings highlight the method’s potential to balance efficiency and accuracy, making it a promising solution for resource-constrained applications.https://ieeexplore.ieee.org/document/10852290/Convolutional neural networkgenetic algorithmeffective weightsimage classification |
| spellingShingle | M. Askari S. Soleimani M. H. Shakoor M. Momeni Eliminating Network Depth: Genetic Algorithm for Parameter Optimization in CNNs IEEE Access Convolutional neural network genetic algorithm effective weights image classification |
| title | Eliminating Network Depth: Genetic Algorithm for Parameter Optimization in CNNs |
| title_full | Eliminating Network Depth: Genetic Algorithm for Parameter Optimization in CNNs |
| title_fullStr | Eliminating Network Depth: Genetic Algorithm for Parameter Optimization in CNNs |
| title_full_unstemmed | Eliminating Network Depth: Genetic Algorithm for Parameter Optimization in CNNs |
| title_short | Eliminating Network Depth: Genetic Algorithm for Parameter Optimization in CNNs |
| title_sort | eliminating network depth genetic algorithm for parameter optimization in cnns |
| topic | Convolutional neural network genetic algorithm effective weights image classification |
| url | https://ieeexplore.ieee.org/document/10852290/ |
| work_keys_str_mv | AT maskari eliminatingnetworkdepthgeneticalgorithmforparameteroptimizationincnns AT ssoleimani eliminatingnetworkdepthgeneticalgorithmforparameteroptimizationincnns AT mhshakoor eliminatingnetworkdepthgeneticalgorithmforparameteroptimizationincnns AT mmomeni eliminatingnetworkdepthgeneticalgorithmforparameteroptimizationincnns |