Miniaturizing neural networks for charge state autotuning in quantum dots

TL;DR

This paper presents tiny neural networks trained on synthetic data to detect charge states in quantum dots, enabling low-power, on-chip autotuning for scalable quantum computing.

Contribution

Develops extremely small neural networks capable of charge state detection and tuning in quantum dots, suitable for implementation in memristor crossbar arrays.

Findings

Neural networks trained on synthetic data transfer effectively to experimental devices.

Tiny neural networks can be implemented in memristor crossbar arrays.

Enables miniaturized, low-power control for quantum dot qubits.

Abstract

A key challenge in scaling quantum computers is the calibration and control of multiple qubits. In solid-state quantum dots, the gate voltages required to stabilize quantized charges are unique for each individual qubit, resulting in a high-dimensional control parameter space that must be tuned automatically. Machine learning techniques are capable of processing high-dimensional data - provided that an appropriate training set is available - and have been successfully used for autotuning in the past. In this paper, we develop extremely small feed-forward neural networks that can be used to detect charge-state transitions in quantum dot stability diagrams. We demonstrate that these neural networks can be trained on synthetic data produced by computer simulations, and robustly transferred to the task of tuning an experimental device into a desired charge state. The neural networks required for this task are sufficiently small as to enable an implementation in existing memristor crossbar arrays in the near future. This opens up the possibility of miniaturizing powerful control elements on low-power hardware, a significant step towards on-chip autotuning in future quantum dot computers.