Author(s)

Sophie Choe, Marek Perkowski

Electrical and Computer Engineering, Portland State University, Portland, OR, USA.

In this paper, classical and continuous variable (CV) quantum neural network hybrid multi-classifiers are presented using the MNIST dataset. Currently available classifiers can classify only up to two classes. The proposed architecture allows networks to classify classes up to n^m classes, where n represents cutoff dimension and m the number of qumodes on photonic quantum computers. The combination of cutoff dimension and probability measurement method in the CV model allows a quantum circuit to produce output vectors of size n^m. They are then interpreted as one-hot encoded labels, padded with n^m - 10 zeros. The total of seven different classifiers is built using 2, 3, …, 6, and 8-qumodes on photonic quantum computing simulators, based on the binary classifier architecture proposed in “Continuous variable quantum neural networks” [1]. They are composed of a classical feed-forward neural network, a quantum data encoding circuit, and a CV quantum neural network circuit. On a truncated MNIST dataset of 600 samples, a 4-qumode hybrid classifier achieves 100% training accuracy.

Quantum Computing, Quantum Machine Learning, Quantum Neural Networks, Continuous Variable Quantum Computing, Photonic Quantum Computing, Classical Quantum Hybrid Model, Quantum MNIST Classification

Choe, S. and Perkowski, M. (2022) Continuous Variable Quantum MNIST Classifiers
—Classical-Quantum Hybrid Quantum Neural Networks. Journal of Quantum Information Science, 12, 37-51. doi: 10.4236/jqis.2022.122005.