Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learning

Abstract

Multiclass classification is of great interest for various applications, for example, it is a common task in computer vision, where one needs to categorize an image into three or more classes. Here we propose a quantum machine learning approach based on quantum convolutional neural networks for solving the multiclass classification problem. The corresponding learning procedure is implemented via TensorFlowQuantum as a hybrid quantum-classical (variational) model, where quantum output results are fed to the softmax activation function with the subsequent minimization of the cross entropy loss via optimizing the parameters of the quantum circuit. Our conceptional improvements here include a new model for a quantum perceptron and an optimized structure of the quantum circuit. We use the proposed approach to solve a 4-class classification problem for the case of the MNIST dataset using eight qubits for data encoding and four ancilla qubits; previous results have been obtained for 3-class classification problems. Our results show that accuracies of our solution are similar to classical convolutional neural networks with comparable numbers of trainable parameters. We expect that our finding provide a new step towards the use of quantum neural networks for solving relevant problems in the NISQ era and beyond.

7 pages, 5 figures, 3 tables

References in corpus (4)

• Quantum Computing
• Quantum-enhanced machine learning
• Decomposing the generalized Toffoli gate with qutrits
• Quantum computing at the quantum advantage threshold: a down-to-business review

Cited by in corpus (10)

• Quantum machine learning for image classification
• Quantum Convolutional Neural Networks are Effectively Classically Simulable
• A Multi-Class SWAP-Test Classifier
• Characterization of variational quantum algorithms using free fermions
• Digital-analog quantum convolutional neural networks for image classification
• On-board classification of underwater images using hybrid classical-quantum CNN based method
• Implementation and Empirical Evaluation of a Quantum Machine Learning Pipeline for Local Classification
• Supervised binary classification of small-scale digit images and weighted graphs with a trapped-ion quantum processor
• Typical Machine Learning Datasets as Low-Depth Quantum Circuits
• Single-Qudit Quantum Neural Networks for Multiclass Classification