Powering Image Classifiers with Quantum Machine Learning

Google researchers demonstrate how quantum computing techniques can be used to classify 28-pixel-by-28-pixel images illuminated by a single photon. By transforming the quantum state of that photon, they show they’re able to achieve “at least” 41.27% accuracy on the popular MNIST corpus of handwritten digits — a 21.27% improvement over classical computing approaches.

Quantum computing-based machine learning mainly focuses on quantum computing hardware that is experimentally challenging to realize due to requiring quantumgates that operate at very low temperature. Instead, we demonstrate the existence of a lower performance and much lower effort island on the accuracy-vs-qubitsgraph that may well be experimentally accessible with room temperature optics.This high temperature “quantum computing toy model” is nevertheless interestingto study as it allows rather accessible explanations of key concepts in quantumcomputing, in particular interference, entanglement, and the measurement process.

We specifically study the problem of classifying an example from the MNIST and Fashion MNIST datasets, subject to the constraint that we have to make aprediction after the detection of the very first photon that passed a coherently illuminated filter showing the example. Whereas a classical set-up in which aphoton is detected after falling on one of the28×28image pixels is limited toa (maximum likelihood estimation) accuracy of21.27%for MNIST, respectively18.27% for Fashion MNIST, we show that the theoretically achievable accuracy when exploiting inference by optically transforming the quantum state of the photon is at least41.27%for MNIST, respectively36.14%for Fashion-MNIST.We show in detail how to train the corresponding transformation with TensorFlow and also explain how this example can serve as a teaching tool for the measurement process in quantum mechanics.


Read the paper here :

Comment here