Learning Quantum Processes with Memory -- Quantum Recurrent Neural Networks
This work addresses the challenge of quantizing recurrent neural networks for quantum machine learning, offering a novel approach to model quantum systems with memory, which is incremental in extending classical concepts to the quantum domain.
The authors tackled the problem of learning quantum processes with memory by proposing fully quantum recurrent neural networks based on dissipative quantum neural networks, demonstrating through classical simulations that these networks can learn complex quantum processes like delay channels and noise mitigation, with numerical results showing strong generalization from small training sets.
Recurrent neural networks play an important role in both research and industry. With the advent of quantum machine learning, the quantisation of recurrent neural networks has become recently relevant. We propose fully quantum recurrent neural networks, based on dissipative quantum neural networks, capable of learning general causal quantum automata. A quantum training algorithm is proposed and classical simulations for the case of product outputs with the fidelity as cost function are carried out. We thereby demonstrate the potential of these algorithms to learn complex quantum processes with memory in terms of the exemplary delay channel, the time evolution of quantum states governed by a time-dependent Hamiltonian, and high- and low-frequency noise mitigation. Numerical simulations indicate that our quantum recurrent neural networks exhibit a striking ability to generalise from small training sets.