Neural-network-designed pulse sequences for robust control of singlet-triplet qubits

TL;DR

This paper demonstrates that neural networks can generate pulse sequences for singlet-triplet qubits, matching or approximating traditional sequences, thus offering a powerful alternative for robust quantum control.

Contribution

The study shows neural networks can efficiently produce both noise-free and noise-correcting pulse sequences for singlet-triplet qubits, simplifying the design process.

Findings

Neural networks replicate known noise-free pulse sequences.

Generated sequences maintain robustness against noise.

Neural network approach offers an alternative to nonlinear equation solving.

Abstract

Composite pulses are essential for universal manipulation of singlet-triplet spin qubits. In the absence of noise, they are required to perform arbitrary single-qubit operations due to the special control constraint of a singlet-triplet qubits; while in a noisy environment, more complicated sequences have been developed to dynamically correct the error. Tailoring these sequences typically requires numerically solving a set of nonlinear equations. Here we demonstrate that these pulse sequences can be generated by a well-trained, double-layer neural network. For sequences designed for the noise-free case, the trained neural network is capable of producing almost exactly the same pulses known in the literature. For more complicated noise-correcting sequences, the neural network produces pulses with slightly different line-shapes, but the robustness against noises remains comparable. These results indicate that the neural network can be a judicious and powerful alternative to existing techniques, in developing pulse sequences for universal fault-tolerant quantum computation.