Semi-Periodic Activation for Time Series Classification
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916521636265984 |
|---|---|
| author | Júnior, José Gilberto Barbosa de Medeiros de Mitri, Andre Guarnier Silva, Diego Furtado |
| author_facet | Júnior, José Gilberto Barbosa de Medeiros de Mitri, Andre Guarnier Silva, Diego Furtado |
| contents | This paper investigates the lack of research on activation functions for neural network models in time series tasks. It highlights the need to identify essential properties of these activations to improve their effectiveness in specific domains. To this end, the study comprehensively analyzes properties, such as bounded, monotonic, nonlinearity, and periodicity, for activation in time series neural networks. We propose a new activation that maximizes the coverage of these properties, called LeakySineLU. We empirically evaluate the LeakySineLU against commonly used activations in the literature using 112 benchmark datasets for time series classification, obtaining the best average ranking in all comparative scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_09889 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Semi-Periodic Activation for Time Series Classification Júnior, José Gilberto Barbosa de Medeiros de Mitri, Andre Guarnier Silva, Diego Furtado Machine Learning Artificial Intelligence This paper investigates the lack of research on activation functions for neural network models in time series tasks. It highlights the need to identify essential properties of these activations to improve their effectiveness in specific domains. To this end, the study comprehensively analyzes properties, such as bounded, monotonic, nonlinearity, and periodicity, for activation in time series neural networks. We propose a new activation that maximizes the coverage of these properties, called LeakySineLU. We empirically evaluate the LeakySineLU against commonly used activations in the literature using 112 benchmark datasets for time series classification, obtaining the best average ranking in all comparative scenarios. |
| title | Semi-Periodic Activation for Time Series Classification |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2412.09889 |