%0 Journal Article
%T Continuous Variable Quantum MNIST Classifiers<br/>¡ªClassical-Quantum Hybrid Quantum Neural Networks
%A Sophie Choe
%A Marek Perkowski
%J Journal of Quantum Information Science
%P 37-51
%@ 2162-576X
%D 2022
%I Scientific Research Publishing
%R 10.4236/jqis.2022.122005
%X 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 <em>n<sup>m</sup></em> classes, where <em>n</em> 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 <em>n<sup>m</sup></em>. They are then interpreted as one-hot encoded labels, padded with <em>n<sup>m</sup></em> <span style=\"white-space:normal;\">-</span> 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¡± <a href=\"#ref1\">[1]</a>. 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.
%K Quantum Computing
%K Quantum Machine Learning
%K Quantum Neural Networks
%K Continuous Variable Quantum Computing
%K Photonic Quantum Computing
%K Classical Quantum Hybrid Model
%K Quantum MNIST Classification
%U http://www.scirp.org/journal/PaperInformation.aspx?PaperID=117971