 Neural networks have achieved great successes in both industry and academia, but developing them on quantum computing devices presents a challenge. To address this issue, we proposed a novel quantum neural network model that uses classical control over single qubits and measurements on real-world quantum systems. This approach reduces the difficulty of physical implementation and enables fast optimization with traditional algorithms. Additionally, it allows quantum computing to be used in a broader range of applications and provides a basis for further research into quantum neural computers. This article was authored by Mingang Zhou, Zhiping Lu, Kuala Yen, and others.