This paper proposes a new model of a real weights quantum neuron exploiting the so-called quantum parallelism which allows for an exponential speedup of computations. The quantum neurons were trained in a classical-quantum approach, considering the delta rule to update the values of the weights in an image database of three distinct patterns. We performed classical simulations and also executed experiments in an actual small-scale quantum processor. The results of the experiments show that the proposed quantum real neuron model has a good generalisation capacity, demonstrating better accuracy than the traditional binary quantum perceptron model.

中文翻译：

---

具有实际权重的量子神经元

本文提出了一种新的真实权重量子神经元模型，它利用所谓的量子并行性来实现计算的指数加速。量子神经元采用经典量子方法进行训练，考虑使用 delta 规则来更新具有三种不同模式的图像数据库中的权重值。我们进行了经典模拟，并在实际的小型量子处理器中进行了实验。实验结果表明，所提出的量子真实神经元模型具有良好的泛化能力，比传统的二元量子感知器模型具有更好的准确性。