High-fidelity quantum state estimation via autoencoder tomography

We investigate the use of supervised machine learning, in the form of a denoising
autoencoder, to simultaneously remove experimental noise while encoding one- and two-qubit quantum state estimates into a minimum number of nodes within the latent layer of a neural network. We decode these latent representations into positive density matrices and compare them to similar estimates obtained via linear inversion and maximum likelihood estimation. Using a superconducting multiqubit chip we experimentally verify that the neural network estimates the quantum state with greater fidelity than either traditional method. Furthermore, we show that the network can be trained using only product states and still achieve high fidelity for entangled states. This simplification of the training overhead permits the network to aid experimental calibration, such as the diagnosis of multi-qubit crosstalk.