Spike-TCN with Depthwise-Separable Convolution and Attention for Efficient Time Series Prediction
Abstract Spiking Neural Networks, known for their event-driven and energy-efficient characteristics, offer promising potential in temporal modeling. However, existing SNN-based models often struggle to capture long-range dependencies and inter-channel interactions, limiting their performance in comp...
Shranjeno v:
| Principais autores: | , , , |
|---|---|
| Format: | Artigo |
| Jezik: | Inglês |
| Izdano: |
Springer
2025-11-01
|
| Serija: | International Journal of Computational Intelligence Systems |
| Teme: | |
| Online dostop: | https://doi.org/10.1007/s44196-025-01063-4 |
| Oznake: |
Brez oznak, prvi označite!
|