DSReLU: A Novel Dynamic Slope Function for Superior Model Training
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914915115073536 |
|---|---|
| author | Chakraborti, Archisman Chaudhuri, Bidyut B |
| author_facet | Chakraborti, Archisman Chaudhuri, Bidyut B |
| contents | This study introduces a novel activation function, characterized by a dynamic slope that adjusts throughout the training process, aimed at enhancing adaptability and performance in deep neural networks for computer vision tasks. The rationale behind this approach is to overcome limitations associated with traditional activation functions, such as ReLU, by providing a more flexible mechanism that can adapt to different stages of the learning process. Evaluated on the Mini-ImageNet, CIFAR-100, and MIT-BIH datasets, our method demonstrated improvements in classification metrics and generalization capabilities. These results suggest that our dynamic slope activation function could offer a new tool for improving the performance of deep learning models in various image recognition tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_09156 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | DSReLU: A Novel Dynamic Slope Function for Superior Model Training Chakraborti, Archisman Chaudhuri, Bidyut B Computer Vision and Pattern Recognition This study introduces a novel activation function, characterized by a dynamic slope that adjusts throughout the training process, aimed at enhancing adaptability and performance in deep neural networks for computer vision tasks. The rationale behind this approach is to overcome limitations associated with traditional activation functions, such as ReLU, by providing a more flexible mechanism that can adapt to different stages of the learning process. Evaluated on the Mini-ImageNet, CIFAR-100, and MIT-BIH datasets, our method demonstrated improvements in classification metrics and generalization capabilities. These results suggest that our dynamic slope activation function could offer a new tool for improving the performance of deep learning models in various image recognition tasks. |
| title | DSReLU: A Novel Dynamic Slope Function for Superior Model Training |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.09156 |