Quantum machine learning is a promising application of quantum computing for data classification. However, most of the previous research focused on binary classification, and there are few studies on multi-classification. The major challenge comes from the limitations of near-term quantum devices on the number of qubits and the size of quantum circuits. In this paper, we propose a hybrid quantum neural network to implement multi-classification of a real-world dataset. We use an average pooling downsampling strategy to reduce the dimensionality of samples, and we design a ladder-like parameterized quantum circuit to disentangle the input states. Besides this, we adopt an all-qubit multi-observable measurement strategy to capture sufficient hidden information from the quantum system. The experimental results show that our algorithm outperforms the classical neural network and performs especially well on different multi-class datasets, which provides some enlightenment for the application of quantum computing to real-world data on near-term quantum processors.

Genetic Algorithm (GA) is a widely used search method, and Quantum Genetic Algorithm (QGA) has been pointed out for several years. While common QGA only refers to the concept of quantum mechanics, and still uses mathematical representations of quantum states to simulate quantum entanglement and superposition, it can’t be realized on a quantum computer. This paper presents an implementable quantum circuit for a genetic algorithm, named as Planar-Weibull Quantum Circuit Genetic Algorithm (PW-QCGA), employing the Weibull function and excitation function through planar matrix coding. It is not only a self-adaptive algorithm that adjusts parameters dynamically, but it can also be executed on quantum computers by constructing parameterized quantum circuits. Experiments on three typical applications show that PW-QCGA not only has obvious advantages on convergence accuracy, search ability, convergence speed, and robustness, but also has higher fidelity on a quantum computer. We hope this work can bring inspiration to other quantum intelligent algorithms.