Enhanced Image Recognition Using Gaussian Boson Sampling
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911020537085952 |
|---|---|
| author | Gong, Si-Qiu Chen, Ming-Cheng Liu, Hua-Liang Su, Hao Gu, Yi-Chao Tang, Hao-Yang Jia, Meng-Hao Deng, Yu-Hao Wei, Qian Wang, Hui Zhong, Han-Sen Jiang, Xiao Li, Li Liu, Nai-Le Lu, Chao-Yang Pan, Jian-Wei |
| author_facet | Gong, Si-Qiu Chen, Ming-Cheng Liu, Hua-Liang Su, Hao Gu, Yi-Chao Tang, Hao-Yang Jia, Meng-Hao Deng, Yu-Hao Wei, Qian Wang, Hui Zhong, Han-Sen Jiang, Xiao Li, Li Liu, Nai-Le Lu, Chao-Yang Pan, Jian-Wei |
| contents | Gaussian boson sampling (GBS) has emerged as a promising quantum computing paradigm, demonstrating its potential in various applications. However, most existing works focus on theoretical aspects or simple tasks, with limited exploration of its capabilities in solving real-world practical problems. In this work, we propose a novel GBS-based image recognition scheme inspired by extreme learning machine (ELM) to enhance the performance of perceptron and implement it using our latest GBS device, Jiuzhang. Our approach utilizes an 8176-mode temporal-spatial hybrid encoding photonic processor, achieving approximately 2200 average photon clicks in the quantum computational advantage regime. We apply this scheme to classify images from the MNIST and Fashion-MNIST datasets, achieving a testing accuracy of 95.86% on MNIST and 85.95% on Fashion-MNIST. These results surpass those of classical method SVC with linear kernel and previous physical ELM-based experiments. Additionally, we explore the influence of three hyperparameters and the efficiency of GBS in our experiments. This work not only demonstrates the potential of GBS in real-world machine learning applications but also aims to inspire further advancements in powerful machine learning schemes utilizing GBS technology. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_19707 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Enhanced Image Recognition Using Gaussian Boson Sampling Gong, Si-Qiu Chen, Ming-Cheng Liu, Hua-Liang Su, Hao Gu, Yi-Chao Tang, Hao-Yang Jia, Meng-Hao Deng, Yu-Hao Wei, Qian Wang, Hui Zhong, Han-Sen Jiang, Xiao Li, Li Liu, Nai-Le Lu, Chao-Yang Pan, Jian-Wei Quantum Physics Gaussian boson sampling (GBS) has emerged as a promising quantum computing paradigm, demonstrating its potential in various applications. However, most existing works focus on theoretical aspects or simple tasks, with limited exploration of its capabilities in solving real-world practical problems. In this work, we propose a novel GBS-based image recognition scheme inspired by extreme learning machine (ELM) to enhance the performance of perceptron and implement it using our latest GBS device, Jiuzhang. Our approach utilizes an 8176-mode temporal-spatial hybrid encoding photonic processor, achieving approximately 2200 average photon clicks in the quantum computational advantage regime. We apply this scheme to classify images from the MNIST and Fashion-MNIST datasets, achieving a testing accuracy of 95.86% on MNIST and 85.95% on Fashion-MNIST. These results surpass those of classical method SVC with linear kernel and previous physical ELM-based experiments. Additionally, we explore the influence of three hyperparameters and the efficiency of GBS in our experiments. This work not only demonstrates the potential of GBS in real-world machine learning applications but also aims to inspire further advancements in powerful machine learning schemes utilizing GBS technology. |
| title | Enhanced Image Recognition Using Gaussian Boson Sampling |
| topic | Quantum Physics |
| url | https://arxiv.org/abs/2506.19707 |