A multi-classification classifier based on variational quantum computation

The interaction between machine learning and quantum physics has given rise to an emerging frontier of quantum machine learning research. In this line, quantum classifiers have received significant attention recently as a quantum device designed to solve the classification problem in machine learning. In this paper, we propose a new variational quantum multi-class classifier that uses log(2)N qubits to represent N labels, converts the labels into different quantum states, and optimizes the circuit parameters by the fidelity between the true label state and the output state. Our method effectively reduces the width of the circuit and lowers the number of auxiliary particles needed from N to log(2)N. We conducted simulation experiments on several datasets. On the MNIST handwritten digits dataset, we achieved 99.8% accuracy for 4 classifications and 97% for 8 classifications. On the CIFAR-10 dataset, we obtained 85.3% accuracy for 8 classifications. Finally, on the CIFAR-100 dataset, we reached 76% accuracy for 16 classifications.