多层神经网络中量子感知器训练的一种无导数方法
A Derivative-free Method for Quantum Perceptron Training in Multi-layered Neural Networks
摘要：
本文提出了一种基于量子感知器的无梯度多层神经网络训练方法。在这里，我们从经典感知器和量子比特（即量子比特）上的基本操作出发，以便根据量子感知器来制定问题。然后，我们利用可测量的运营商，以符合马尔可夫过程的方式来定义网络的状态。这产生了与量子力学一致的狄拉克-冯·诺依曼公式。此外，这里提出的公式具有计算效率不受网络层数影响的优点。这与量子计算的自然效率相结合，可能意味着效率的显著提高，特别是对于深度网络。最后，但并非最不重要的是，这里的发展在本质上是相当普遍的，因为这里提出的方法也可以用于在传统计算机上实现的量子启发神经网络。
英文摘要：
In this paper, we present a gradient-free approach for training multi-layered neural networks based upon quantum perceptrons. Here, we depart from the classical perceptron and the elemental operations on quantum bits, i.e. qubits, so as to formulate the problem in terms of quantum perceptrons. We then make use of measurable operators to define the states of the network in a manner consistent with a Markov process. This yields a Dirac-Von Neumann formulation consistent with quantum mechanics. Moreover, the formulation presented here has the advantage of having a computational efficiency devoid of the number of layers in the network. This, paired with the natural efficiency of quantum computing, can imply a significant improvement in efficiency, particularly for deep networks. Finally, but not least, the developments here are quite general in nature since the approach presented here can also be used for quantum-inspired neural networks implemented on conventional computers.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
