Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2312.16503 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916231506821120 |
|---|---|
| author | Köster, Felix Kanno, Kazutaka Ohkubo, Jun Uchida, Atsushi |
| author_facet | Köster, Felix Kanno, Kazutaka Ohkubo, Jun Uchida, Atsushi |
| contents | Photonic reservoir computing has been successfully utilized in time-series prediction as the need for hardware implementations has increased. Prediction of chaotic time series remains a significant challenge, an area where the conventional reservoir computing framework encounters limitations of prediction accuracy. We introduce an attention mechanism to the reservoir computing model in the output stage. This attention layer is designed to prioritize distinct features and temporal sequences, thereby substantially enhancing the prediction accuracy. Our results show that a photonic reservoir computer enhanced with the attention mechanism exhibits improved prediction capabilities for smaller reservoirs. These advancements highlight the transformative possibilities of reservoir computing for practical applications where accurate prediction of chaotic time series is crucial. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2312_16503 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Attention-Enhanced Reservoir Computing Köster, Felix Kanno, Kazutaka Ohkubo, Jun Uchida, Atsushi Emerging Technologies Machine Learning Photonic reservoir computing has been successfully utilized in time-series prediction as the need for hardware implementations has increased. Prediction of chaotic time series remains a significant challenge, an area where the conventional reservoir computing framework encounters limitations of prediction accuracy. We introduce an attention mechanism to the reservoir computing model in the output stage. This attention layer is designed to prioritize distinct features and temporal sequences, thereby substantially enhancing the prediction accuracy. Our results show that a photonic reservoir computer enhanced with the attention mechanism exhibits improved prediction capabilities for smaller reservoirs. These advancements highlight the transformative possibilities of reservoir computing for practical applications where accurate prediction of chaotic time series is crucial. |
| title | Attention-Enhanced Reservoir Computing |
| topic | Emerging Technologies Machine Learning |
| url | https://arxiv.org/abs/2312.16503 |