Rapid training of quantum recurrent neural networks
This work addresses the training efficiency problem for time series prediction tasks, offering a potential quantum advantage, but it appears incremental as it extends existing RNN concepts with quantum resources.
The authors tackled the slow and energy-intensive training of recurrent neural networks for time series prediction by proposing a continuous-variable quantum RNN, which demonstrated faster convergence in fewer epochs and lower losses with fewer parameters than classical networks.
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.