Physics-informed neural network for quantum control of NMR registers

TL;DR

This paper demonstrates a physics-informed neural network approach for quantum control in NMR systems, enabling adaptable control sequences for quantum gate synthesis and state preparation with experimental validation.

Contribution

It introduces a novel PINN-based method for quantum control that encodes control sequences in network parameters, allowing hardware-agnostic implementation and improved flexibility.

Findings

Successful experimental implementation of CNOT gate on NMR register.

Efficient transfer to long-lived singlet state demonstrated.

Numerical analysis of control sequence robustness and noise effects.

Abstract

Classical and quantum machine learning are being increasingly applied to various tasks in quantum information technologies. Here, we present an experimental demonstration of quantum control using a physics-informed neural network (PINN). PINN's salient feature is how it encodes the entire control sequence in terms of its network parameters. This feature enables the control sequence to be later adopted to any hardware with optimal time discretization, which contrasts with conventional methods involving a priory time discretization. Here, we discuss two important quantum information tasks: gate synthesis and state preparation. First, we demonstrate quantum gate synthesis by designing a two-qubit CNOT gate and experimentally implementing it on a heteronuclear two-spin NMR register. Second, we demonstrate quantum state preparation by designing a control sequence to efficiently transfer the thermal state into the long-lived singlet state and experimentally implement it on a homonuclear two-spin NMR register. We present a detailed numerical analysis of the PINN control sequences regarding bandwidth, discretization levels, control field errors, and external noise.