Completely quantum neural networks
Completely quantum neural networks
复制标题
DOI：
10.1103/physreva.106.022601
复制
发表时间：
2022-08-01
影响因子：
2.9
通讯作者：
Spannowsky, Michael
中科院分区：
文献类型：
--
作者：
Abel, Steve;Criado, Juan C.;Spannowsky, Michael
人工神经网络是现代深度学习算法的核心。我们描述了如何在不引入任何经典元素的情况下，在量子退火炉中嵌入和训练通用神经网络。为了在最先进的量子退火炉上实现该网络，我们开发了三个关键部分：对网络的自由参数进行二进制编码；对激活函数进行多项式逼近；以及将二进制高阶多项式化为二次多项式。总而言之，这些想法允许将损失函数编码为伊辛模型哈密顿量。然后，量子退火器通过寻找基态来训练网络。我们对一个基本网络进行了实现，并说明了量子训练的优势：它在寻找损失函数的全局最小值方面的一致性，以及网络训练在单个退火步收敛的事实，从而在保持高分类性能的同时导致较短的训练时间。在使用量子退火器训练网络后，可以使用相同设计的经典网络算法中的量子网络权重进行推理。我们的方法为一般机器学习模型的量子训练开辟了一条途径。
Artificial neural networks are at the heart of modern deep learning algorithms. We describe how to embed and train a general neural network in a quantum annealer without introducing any classical element in training. To implement the network on a state-of-the-art quantum annealer, we develop three crucial ingredients: binary encoding the free parameters of the network; polynomial approximation of the activation function; and reduction of binary higher-order polynomials into quadratic ones. Together, these ideas allow encoding the loss function as an Ising model Hamiltonian. The quantum annealer then trains the network by finding the ground state. We implement this for an elementary network and illustrate the advantages of quantum training: its consistency in finding the global minimum of the loss function and the fact that the network training converges in a single annealing step, which leads to short training times while maintaining a high classification performance. After training the network using a quantum annealer, one can then use the quantum network weights in a classical network algorithm of identical design for inference. Our approach opens an avenue for the quantum training of general machine learning models.