Enhancing CNN Classification with Lamarckian Memetic Algorithms and Local Search
Fuente:
arXiv
Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910780447784960 |
|---|---|
| author | Ghosh, Akhilbaran Kalidindi, Rama Sai Adithya |
| author_facet | Ghosh, Akhilbaran Kalidindi, Rama Sai Adithya |
| contents | Optimization is critical for optimal performance in deep neural networks (DNNs). Traditional gradient-based methods often face challenges like local minima entrapment. This paper explores population-based metaheuristic optimization algorithms for image classification networks. We propose a novel approach integrating a two-stage training technique with population-based optimization algorithms incorporating local search capabilities. Our experiments demonstrate that the proposed method outperforms state-of-the-art gradient-based techniques, such as ADAM, in accuracy and computational efficiency, particularly with high computational complexity and numerous trainable parameters. The results suggest that our approach offers a robust alternative to traditional methods for weight optimization in convolutional neural networks (CNNs). Future work will explore integrating adaptive mechanisms for parameter tuning and applying the proposed method to other types of neural networks and real-time applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_20234 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing CNN Classification with Lamarckian Memetic Algorithms and Local Search Ghosh, Akhilbaran Kalidindi, Rama Sai Adithya Computer Vision and Pattern Recognition Optimization is critical for optimal performance in deep neural networks (DNNs). Traditional gradient-based methods often face challenges like local minima entrapment. This paper explores population-based metaheuristic optimization algorithms for image classification networks. We propose a novel approach integrating a two-stage training technique with population-based optimization algorithms incorporating local search capabilities. Our experiments demonstrate that the proposed method outperforms state-of-the-art gradient-based techniques, such as ADAM, in accuracy and computational efficiency, particularly with high computational complexity and numerous trainable parameters. The results suggest that our approach offers a robust alternative to traditional methods for weight optimization in convolutional neural networks (CNNs). Future work will explore integrating adaptive mechanisms for parameter tuning and applying the proposed method to other types of neural networks and real-time applications. |
| title | Enhancing CNN Classification with Lamarckian Memetic Algorithms and Local Search |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.20234 |