paper-with-me

홈 › Papers

PGKET: A Photonic Gaussian Kernel Enhanced Transformer

2025-07-25 · Ren-Xin Zhao arxiv

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.

📄 PDF Abstract BibTeX arXiv:2507.19041

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Photonic Quantum-Enhanced Knowledge Distillation

2026-03-16 · Kuan-Cheng Chen, Shang Yu, Chen-Yu Liu, Samuel Yen-Chi Chen 외 arxiv

Photonic quantum processors naturally produce intrinsically stochastic measurement outcomes, offering a hardware-native source of structured randomness that can be exploited during machine-learning training. Here we intr…

Knowledge Distillation

Photonic Quantum Computing For Polymer Classification

2022-11-22 · Alexandrina Stoyanova, Taha Hammadia, Arno Ricou, Bogdan Penkovsky

We present a hybrid classical-quantum approach to the binary classification of polymer structures. Two polymer classes visual (VIS) and near-infrared (NIR) are defined based on the size of the polymer gaps. The hybrid ap…

Binary ClassificationClassification

Toward Large-Scale Photonics-Empowered AI Systems: From Physical Design Automation to System-Algorithm Co-Exploration

2025-12-31 · Ziang Yin, Hongjian Zhou, Nicholas Gangi, Meng Zhang 외 arxiv

In this work, we identify three considerations that are essential for realizing practical photonic AI systems at scale: (1) dynamic tensor operation support for modern models rather than only weight-static kernels, espec…

Photonics-Enhanced Graph Convolutional Networks

2025-12-17 · Yuan Wang, Oleksandr Kyriienko arxiv

Photonics can offer a hardware-native route for machine learning (ML). However, efficient deployment of photonics-enhanced ML requires hybrid workflows that integrate optical processing with conventional CPU/GPU based ne…

Optimizing Photonic Nanostructures via Multi-fidelity Gaussian Processes

2018-11-15 · Jialin Song, Yury S. Tokpanov, Yuxin Chen, Dagny Fleischman 외

We apply numerical methods in combination with finite-difference-time-domain (FDTD) simulations to optimize transmission properties of plasmonic mirror color filters using a multi-objective figure of merit over a five-di…

Gaussian Processes