arXiv · 2212.00080
Enhancing Qubit Readout with Autoencoders
Abstract
In addition to the need for stable and precisely controllable qubits, quantum computers take advantage of good readout schemes. Superconducting qubit states can be inferred from the readout signal transmitted through a dispersively coupled resonator. This work proposes a novel readout classification method for superconducting qubits based on a neural network pre-trained with an autoencoder approach. A neural network is pre-trained with qubit readout signals as autoencoders in order to extract relevant features from the data set. Afterwards, the pre-trained network inner layer values are used to perform a classification of the inputs in a supervised manner. We demonstrate that this method can enhance classification performance, particularly for short and long time measurements where more traditional methods present lower performance.
Explore related subjects
Keep this discovery
Piero Luchi, Paolo E. Trevisanutto, Alessandro Roggero, Jonathan L. DuBois, Yaniv J. Rosen, Francesco Turro, Valentina Amitrano, Francesco Pederiva. 2022-11-30. Enhancing Qubit Readout with Autoencoders. https://doi.org/10.1103/physrevapplied.20.014045
Cite the original work for its findings. Save a collection to share your selection of sources.