Rapid training of quantum recurrent neural networks
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2022
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915312039886848 |
|---|---|
| author | Siemaszko, Michał Buraczewski, Adam Saux, Bertrand Le Stobińska, Magdalena |
| author_facet | Siemaszko, Michał Buraczewski, Adam Saux, Bertrand Le Stobińska, Magdalena |
| contents | Time series prediction is essential for human activities in diverse areas. A common approach to this task is to harness Recurrent Neural Networks (RNNs). However, while their predictions are quite accurate, their learning process is complex and, thus, time and energy consuming. Here, we propose to extend the concept of RRNs by including continuous-variable quantum resources in it, and to use a quantum-enhanced RNN to overcome these obstacles. The design of the Continuous-Variable Quantum RNN (CV-QRNN) is rooted in the continuous-variable quantum computing paradigm. By performing extensive numerical simulations, we demonstrate that the quantum network is capable of learning-time dependence of several types of temporal data, and that it converges to the optimal weights in fewer epochs than a classical network. Furthermore, for a small number of trainable parameters, it can achieve lower losses than its classical counterpart. CV-QRNN can be implemented using commercially available quantum-photonic hardware. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2207_00378 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Rapid training of quantum recurrent neural networks Siemaszko, Michał Buraczewski, Adam Saux, Bertrand Le Stobińska, Magdalena Quantum Physics Machine Learning Time series prediction is essential for human activities in diverse areas. A common approach to this task is to harness Recurrent Neural Networks (RNNs). However, while their predictions are quite accurate, their learning process is complex and, thus, time and energy consuming. Here, we propose to extend the concept of RRNs by including continuous-variable quantum resources in it, and to use a quantum-enhanced RNN to overcome these obstacles. The design of the Continuous-Variable Quantum RNN (CV-QRNN) is rooted in the continuous-variable quantum computing paradigm. By performing extensive numerical simulations, we demonstrate that the quantum network is capable of learning-time dependence of several types of temporal data, and that it converges to the optimal weights in fewer epochs than a classical network. Furthermore, for a small number of trainable parameters, it can achieve lower losses than its classical counterpart. CV-QRNN can be implemented using commercially available quantum-photonic hardware. |
| title | Rapid training of quantum recurrent neural networks |
| topic | Quantum Physics Machine Learning |
| url | https://arxiv.org/abs/2207.00378 |