ReCA: A Parametric ReLU Composite Activation Function
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912501860401152 |
|---|---|
| author | Chidiac, John Azar, Danielle |
| author_facet | Chidiac, John Azar, Danielle |
| contents | Activation functions have been shown to affect the performance of deep neural networks significantly. While the Rectified Linear Unit (ReLU) remains the dominant choice in practice, the optimal activation function for deep neural networks remains an open research question. In this paper, we propose a novel parametric activation function, ReCA, based on ReLU, which has been shown to outperform all baselines on state-of-the-art datasets using different complex neural network architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_08994 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ReCA: A Parametric ReLU Composite Activation Function Chidiac, John Azar, Danielle Machine Learning Activation functions have been shown to affect the performance of deep neural networks significantly. While the Rectified Linear Unit (ReLU) remains the dominant choice in practice, the optimal activation function for deep neural networks remains an open research question. In this paper, we propose a novel parametric activation function, ReCA, based on ReLU, which has been shown to outperform all baselines on state-of-the-art datasets using different complex neural network architectures. |
| title | ReCA: A Parametric ReLU Composite Activation Function |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2504.08994 |