Rapid training of quantum recurrent neural networks

Abstract

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.

References in corpus (6)

• An introduction to quantum machine learning
• Quantum advantage in learning from experiments
• Image and Video Compression with Neural Networks: A Review
• Continuous-Variable Instantaneous Quantum Computing is hard to sample
• A Quantum Model for Coherent Ising Machines: Discrete-time Measurement Feedback Formulation
• Experimental quantum stochastic walks simulating associative memory of Hopfield neural networks

Cited by in corpus (5)

• Approximately Equivariant Quantum Neural Network for $p4m$ Group Symmetries in Images
• Density Matrix Emulation of Quantum Recurrent Neural Networks for Multivariate Time Series Prediction
• A Survey of Classical And Quantum Sequence Models
• FRQI Pairs method for image classification using Quantum Recurrent Neural Network
• A Quantum Variational Approach to Prototypical Recurrent Unit