Deep Neural Network Discrimination of Multiplexed Superconducting Qubit States

TL;DR

This paper demonstrates that neural networks can improve multi-qubit state discrimination fidelity in superconducting quantum systems, reducing error rates and compensating for system nonidealities, thus aiding scalable quantum computing.

Contribution

The authors introduce neural network-based multi-qubit readout that outperforms traditional methods, offering a scalable and high-fidelity solution for quantum state discrimination.

Findings

Neural networks increase qubit-state-assignment fidelity.

Error rate reduced by up to 25% compared to traditional discriminators.

System-dependent nonidealities like crosstalk are effectively compensated.

Abstract

Demonstrating a quantum computational advantage will require high-fidelity control and readout of multi-qubit systems. As system size increases, multiplexed qubit readout becomes a practical necessity to limit the growth of resource overhead. Many contemporary qubit-state discriminators presume single-qubit operating conditions or require considerable computational effort, limiting their potential extensibility. Here, we present multi-qubit readout using neural networks as state discriminators. We compare our approach to contemporary methods employed on a quantum device with five superconducting qubits and frequency-multiplexed readout. We find that fully-connected feedforward neural networks increase the qubit-state-assignment fidelity for our system. Relative to contemporary discriminators, the assignment error rate is reduced by up to 25% due to the compensation of system-dependent nonidealities such as readout crosstalk which is reduced by up to one order of magnitude. Our work demonstrates a potentially extensible building block for high-fidelity readout relevant to both near-term devices and future fault-tolerant systems.