Machine learning has been used in research from medical science to image processing and more.
Now University of Melbourne engineers hope to apply it to quantum computing. A type of machine learning known as a convolutional neural network (CNN) is a powerful tool for image recognition problems that can be trained on thousands of pictures, allowing it to recognise unknown images and perform classifications — meaning it could be used to establish the spatial metrology of qubit atoms.
The work, led by Senior Lecturer Muhammad Usman, was reported in NPJ Computational Materials.
“The CNN classified the test images with an accuracy of above 98 per cent, confirming that this machine learning-based technique could process qubit measurement data with high-throughput, high precision, and minimal human interaction,” said Usman and his colleague Professor Lloyd Hollenberg.
