WEKO3
アイテム
Fast and scalable classical machine-learning algorithm with similar performance to quantum circuit learning
https://repo.qst.go.jp/records/84669
https://repo.qst.go.jp/records/846695b717107-c159-4b2c-8a1e-f125bc7567b1
| Item type | 学術雑誌論文 / Journal Article(1) | |||||
|---|---|---|---|---|---|---|
| 公開日 | 2022-01-09 | |||||
| タイトル | ||||||
| タイトル | Fast and scalable classical machine-learning algorithm with similar performance to quantum circuit learning | |||||
| 言語 | ||||||
| 言語 | jpn | |||||
| 資源タイプ | ||||||
| 資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||
| 資源タイプ | journal article | |||||
| アクセス権 | ||||||
| アクセス権 | metadata only access | |||||
| アクセス権URI | http://purl.org/coar/access_right/c_14cb | |||||
| 著者 |
Naoko, Koide-Majima
× Naoko, Koide-Majima× Majima, Kei× Kei, Majima |
|||||
| 抄録 | ||||||
| 内容記述タイプ | Abstract | |||||
| 内容記述 | The application of near-term quantum devices to machine learning (ML) has attracted much attention. Recently, Mitarai et al. [Phys. Rev. A 98, 032309 (2018)] proposed a framework to use a quantum circuit for ML tasks, called quantum circuit learning (QCL). Due to the use of a quantum circuit, QCL employs an exponentially high-dimensional Hilbert space as its feature space. However, its efficiency compared to classical algorithms remains unexplored. Here, we present a classical ML algorithm that uses the same Hilbert space. In numerical simulations, our algorithm demonstrates similar performance to QCL for several ML tasks, providing a perspective for the computational and memory efficiency of quantum ML algorithms. | |||||
| 書誌情報 |
Physical Review A 巻 104, 号 6, p. 062411, 発行日 2021-12 |
|||||
| 出版者 | ||||||
| 出版者 | American Physical Society | |||||
| ISSN | ||||||
| 収録物識別子タイプ | ISSN | |||||
| 収録物識別子 | 1050-2947 | |||||
| DOI | ||||||
| 識別子タイプ | DOI | |||||
| 関連識別子 | 10.1103/PhysRevA.104.062411 | |||||
| 関連サイト | ||||||
| 識別子タイプ | URI | |||||
| 関連識別子 | https://journals.aps.org/pra/abstract/10.1103/PhysRevA.104.062411 | |||||
