RECURRENT QUANTUM NEURAL NETWORKS: A REVIEW

RECURRENT QUANTUM NEURAL NETWORKS: A REVIEW

Jesus, Gleydson Fernandes de; Silva, Valéria Loureiro da

Full article:

The analysis of historical data allows the execution of predictive tasks such as weather and stock price forecasting. To achieve these goals, Recurrent Neural Networks are implemented in classical computers and, in recent years, quantum methods have also emerged to perform prediction tasks based on the analysis of historical series, which have been called Quantum Recurrent Neural Network (QRNN). The objective of this work is to identify and review the main QRNNs discussed in the literature. A literature search in google scholar resulted in eight relevant papers that were reviewed. In general, the QRNNs show better training accuracy and stability compared to classical methods. It is not possible to speak of a training time advantage with the noisy and low-scale quantum computers currently available.

The analysis of historical data allows the execution of predictive tasks such as weather and stock price forecasting. To achieve these goals, Recurrent Neural Networks are implemented in classical computers and, in recent years, quantum methods have also emerged to perform prediction tasks based on the analysis of historical series, which have been called Quantum Recurrent Neural Network (QRNN). The objective of this work is to identify and review the main QRNNs discussed in the literature. A literature search in google scholar resulted in eight relevant papers that were reviewed. In general, the QRNNs show better training accuracy and stability compared to classical methods. It is not possible to speak of a training time advantage with the noisy and low-scale quantum computers currently available.

Palavras-chave: - -

DOI: 10.5151/siintec2023-306159

Referências bibliográficas

• [1] "[1] EKMAN, Magnus. Learning Deep Learning: Theory and Practice of Neural Networks, Computer Vision, Natural Language Processing, and Transformers Using TensorFlow. Addison-Wesley Professional; 1st edition (July 19, 2021). [2] SCHULD, Maria. Machine Learning with Quantum Computers. Springer; 2nd 2021 ed. edição (19 outubro 2022). [3] BAUSCH, Johannes. Recurrent Quantum Neural Networks. 34th Conference on Neural Information Processing Systems (NeurIPS 2020), Vancouver, Canada. [4] EMMANOULOPOULOS, Dimitrios; DIMOSKA, Sofia. Quantum Machine Learning
• [2] in Finance: Time Series Forecasting. ArXiv, Feb 2020.
• [3] YEN-CHI, Samuel. Quantum Long Shot-Term Memory. ArXiv, Sep 2020.
• [4] TAKAKI, Yuto. Learning temporal data with variatonal quantum recurrent neural
• [5] network. ArXiv, Dec 2020.
• [6] LI, Yanan. Quantum Recurrent Neural Networks for Sequential Learning. ArXiv,
• [7] Feb 2023.
• [8] SIEMASZKO, Michał et al. Rapid training of quantum recurrent neural networks.
• [9] ArXiv, Mar 2023.
• [10] NIKOLOSKA, Ivana et al. Time-Warping Invariant Quantum Recurrent Neural
• [11] Networks via Quantum-Classical Adaptive Gating., ArXiv, Jun 2023.
• [12] OĞUR, Beşir. The effect of superposition and entanglement on hybrid quantum
• [13] machine learning for weather forecasting. Quantum Information and Computation,
• [14] Vol. 23, No. 3&4 (2023) 0181-0194.
• [15] Cao et al, Quantum Neuron: an elementary building block for machine learning
• [16] on quantum computers. ArXiv, Nov 2017."

Como citar:

Jesus, Gleydson Fernandes de; Silva, Valéria Loureiro da; "RECURRENT QUANTUM NEURAL NETWORKS: A REVIEW", p-357-365. In: . São Paulo: Blucher, 2023.
ISSN 23577592, DOI 10.5151/siintec2023-306159