PGKET: A Photonic Gaussian Kernel Enhanced Transformer
Fuente:
arXiv
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908466718703616 |
|---|---|
| author | Zhao, Ren-Xin |
| author_facet | Zhao, Ren-Xin |
| contents | Self-Attention Mechanisms (SAMs) enhance model performance by extracting key information but are inefficient when dealing with long sequences. To this end, a photonic Gaussian Kernel Enhanced Transformer (PGKET) is proposed, based on the Photonic Gaussian Kernel Self-Attention Mechanism (PGKSAM). The PGKSAM calculates the Photonic Gaussian Kernel Self-Attention Score (PGKSAS) using photon interferometry and superposition to process multiple inputs in parallel. Experimental results show that PGKET outperforms some state-of-the-art transformers in multi-classification tasks on MedMNIST v2 and CIFAR-10, and is expected to improve performance in complex tasks and accelerate the convergence of Photonic Computing (PC) and machine learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_19041 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PGKET: A Photonic Gaussian Kernel Enhanced Transformer Zhao, Ren-Xin Quantum Physics Computer Vision and Pattern Recognition Self-Attention Mechanisms (SAMs) enhance model performance by extracting key information but are inefficient when dealing with long sequences. To this end, a photonic Gaussian Kernel Enhanced Transformer (PGKET) is proposed, based on the Photonic Gaussian Kernel Self-Attention Mechanism (PGKSAM). The PGKSAM calculates the Photonic Gaussian Kernel Self-Attention Score (PGKSAS) using photon interferometry and superposition to process multiple inputs in parallel. Experimental results show that PGKET outperforms some state-of-the-art transformers in multi-classification tasks on MedMNIST v2 and CIFAR-10, and is expected to improve performance in complex tasks and accelerate the convergence of Photonic Computing (PC) and machine learning. |
| title | PGKET: A Photonic Gaussian Kernel Enhanced Transformer |
| topic | Quantum Physics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.19041 |