Hybrid neural network - quantum simulator

The recent advances in qubit manufacturing and coherent control of synthetic quantum matter are leading to a new generation of intermediate-scale quantum hardware, with promising progress towards scalable quantum simulation of strongly-correlated systems. In order to enhance the capabilities of this class of quantum devices, some of the more arduous experimental tasks can be off-loaded to classical algorithms running on conventional computers. In particular, generative neural networks trained on measurement data can be implemented to obtain an approximate reconstruction of the experimental wavefunction, allowing specialized measurements which are either costly or not accessible in the experimental setup. I will present this classical-quantum hybridization for quantum hardware based on trapped ultra-cold atoms and superconducting qubits.