We present a model of Continuous Variable Quantum Perceptron (CVQP), also referred to as neuron in the following, whose architecture implements a classical perceptron. The necessary nonlinearity is obtained via measuring the output qubit and using the measurement outcome as input to an activation function. The latter is chosen to be the so-called Rectified linear unit (ReLu) activation function by virtue of its practical feasibility and the advantages it provides in learning tasks. The encoding of classical data into realistic finitely squeezed states and the use of superposed (entangled) input states for specific binary problems are discussed.

中文翻译：

---

连续可变量子感知器

我们提出了一个连续变量量子感知器（CVQP）模型，以下也称为神经元，其架构实现了经典感知器。通过测量输出量子比特并将测量结果用作激活函数的输入来获得必要的非线性。选择后者作为所谓的整流线性单元（ReLu）激活函数，是因为它的实际可行性和它在学习任务中提供的优势。讨论了将经典数据编码为现实的有限压缩状态以及针对特定二进制问题使用叠加（纠缠）输入状态。