Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Identification of quantum generative circuits with parallel quantum neural network

Zheping Wu, Xiaopeng Huang, Hengyue Jia, Haobin Shi, Wei-Wei Zhang

TL;DR

This work generated W-like states with eight generative quantum circuits realizing the generative quantum denoising diffusion probabilistic models (QDDPM) and proposes parallel quantum embedding neural network (ParaQuanNet) for the efficient identification of quantum generative circuits via classifications of the corresponding output data.

Abstract

The rapid emergence of quantum technology has raised new challenges in distinguishing various quantum circuits of similar functions. In this work, we propose parallel quantum embedding neural network (ParaQuanNet) for the efficient identification of quantum generative circuits via classifications of the corresponding output data. Specifically, we generated W-like states with eight generative quantum circuits realizing the generative quantum denoising diffusion probabilistic models (QDDPM). Our ParaQuanNet can classify these eight classes of generated quantum data with an accuracy of {$99.5\%$}, even though all of them are trained to generate the same types of quantum data. With a novel design of parallel quantum embedding unit (PQEU) in our neural networks, our ParaQuanNet enables the quantum kernel circuit parallelly process all the receptive fields of quantum data, which empowers the quantum data processing efficiency. We also integrate the mutually unbiased measurements into our ParaQuanNet and further improve its performance. We apply our ParaQuanNet on the classification of classical data sets and demonstrate a good performance of quantum neural networks on these tasks. Our approach demonstrates good robustness to noisy data and the circuit-level noise with a Python realization in a classical GPU. Our results highlight ParaQuanNet as a scalable and effective framework for quantum circuits identification, contributing to the broader development of quantum machine intelligence.

Identification of quantum generative circuits with parallel quantum neural network

TL;DR

This work generated W-like states with eight generative quantum circuits realizing the generative quantum denoising diffusion probabilistic models (QDDPM) and proposes parallel quantum embedding neural network (ParaQuanNet) for the efficient identification of quantum generative circuits via classifications of the corresponding output data.

Abstract

The rapid emergence of quantum technology has raised new challenges in distinguishing various quantum circuits of similar functions. In this work, we propose parallel quantum embedding neural network (ParaQuanNet) for the efficient identification of quantum generative circuits via classifications of the corresponding output data. Specifically, we generated W-like states with eight generative quantum circuits realizing the generative quantum denoising diffusion probabilistic models (QDDPM). Our ParaQuanNet can classify these eight classes of generated quantum data with an accuracy of {}, even though all of them are trained to generate the same types of quantum data. With a novel design of parallel quantum embedding unit (PQEU) in our neural networks, our ParaQuanNet enables the quantum kernel circuit parallelly process all the receptive fields of quantum data, which empowers the quantum data processing efficiency. We also integrate the mutually unbiased measurements into our ParaQuanNet and further improve its performance. We apply our ParaQuanNet on the classification of classical data sets and demonstrate a good performance of quantum neural networks on these tasks. Our approach demonstrates good robustness to noisy data and the circuit-level noise with a Python realization in a classical GPU. Our results highlight ParaQuanNet as a scalable and effective framework for quantum circuits identification, contributing to the broader development of quantum machine intelligence.
Paper Structure (9 sections, 12 equations, 9 figures, 4 tables, 1 algorithm)

This paper contains 9 sections, 12 equations, 9 figures, 4 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. quantum AI-generated data identification with parallel quantum neural network
  3. Quantum generative circuits
  4. Parallel quantum embedding network
  5. Mutual unbiased measurements empowered ParaQuanNet
  6. Quantum generative circuits identificaiton with our ParaQuanNet
  7. experimental settings
  8. Classification of classical data with our ParaQuanNet
  9. Conclusion

Figures (9)

  • Figure 1: Sketch of our scheme for quantum identification of quantum AI-generated data. Top: the quantum data generated from various quantum generative circuits. Middle: the workflow of our ParaQuanNet. Bottom: the structure of the proposed PQEU.
  • Figure 2: The eight structures of quantum W-like states generation circuits used for our data generation.
  • Figure 3: Top: Convention quantum neural network data flow. Bottom: the sketch of our PQEU process data flow.
  • Figure 4: Sketch of our two proposed measurement modes: (a) S-MUB and (b) A-MUB, where the eyes represent the quantum observations/measurements.
  • Figure 5: The classification accuracy for the eight classes of quantum data.
  • ...and 4 more figures