随着深度学习的广泛应用，神经网络模型的数据自生成以及概率模拟等功能在量子态重构与估计方面的应用得到人们关注。通过对量子态的各种不同的数学表示，引导到神经网络量子态的不同表示；从量子态不同物理变量之间的关系，推导出相应神经网络结构上的输入/输出之间的非线性映射关系，为采用不同类型的神经网络模型根据自身数据自生成以及概率模拟功能，实现量子态估计应用，提供网络函数关系及其数据生成的理论设计基础。
With wide application of deep learning, applications of data self-generation and probability simulation of neural network models in quantum state reconstruction and estimation have attracted people's attention. In this paper, from various mathematical representations of quantum states, we derive different representations of quantum states in neural networks. Nonlinear mapping relationships between input/output on corresponding neural network structures are deduced from the relationship between different physical variables of quantum state. This work provides a theoretical design basis of network function relationship and data generation for using different types of neural network models to realize quantum state estimation by means of their own data self-generation and probability simulation function.
[1] D'Alessandro D. On quantum state observability and measurement[J]. Journal of Physics A: Mathematical and General, 2003, 36(37): 9721-9735
[2] Fano U. Description of states in quantum mechanics by density matrix and operator techniques[J]. Reviews of Modern Physics, 1957, 29(1): 74-93.
[3] Smith A, Riofrío C A, Anderson B E, et al. Quantum state tomography by continuous measurement and compressed sensing[J]. Physical Review A, 2013, 87(3): 030102.
[4] Li K, Zhang J, Cong S. Fast reconstruction of high-qubit quantum states via low rate measurements[J]. Physical Review A, 2017, 96(1): 012334.
[5] Zhang J J, Cong S, Ling Q, et al. Quantum state filter with disturbance and noise[J]. IEEE Transactions on Automatic Control, 2020, 65(7): 2856-2866.
[6] Xin T, Lu S R, Cao N, et al. Local-measurement-based quantum state tomography via neural networks[J]. NPJ Quantum Information, 2019, 5(1): 109.
[7] Lohani S, Kirby B T, Brodsky M, et al. Machine learning assisted quantum state estimation[J]. Machine Learning: Science and Technology, 2020, 1(3): 035007.
[8] Xu Q, Xu S Q. Neural network state estimation for full quantum state tomography[J]. arXiv e-prints, 2018: 1811.06654.
[9] 潘成威, 丛爽 . 基于宽度神经网络的 2比特量子态的估计[C]//第22届中国系统仿真年会. 合肥: 中国科学技术大学, 2021: 80-84.
[10] Zyczkowski K, Penson K A, Nechita I, et al. Generating random density matrices[J]. Journal of Mathematical Physics, 2011, 52(6): 062201.
[11] 蒋文杰, 邓东灵 . 神经网络量子态及其应用[J]. 物理,2021, 50(2): 76-83.
[12] Hinton G E. Training products of experts by minimizing contrastive divergence[J]. Neural Computation, 2002, 14 (8): 1771-1800.
[13] Torlai G, Melko R G. Latent space purification via neural density operators[J]. Physical Review Letters, 2018, 120(24): 240503.
