{"ID":2890376,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.19041","arxiv_id":"2507.19041","title":"PGKET: A Photonic Gaussian Kernel Enhanced Transformer","abstract":"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.","short_abstract":"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...","url_abs":"https://arxiv.org/abs/2507.19041","url_pdf":"https://arxiv.org/pdf/2507.19041v1","authors":"[\"Ren-Xin Zhao\"]","published":"2025-07-25T07:52:24Z","proceeding":"quant-ph","tasks":"[\"quant-ph\",\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false}