CVIU Lab, Department of Computer Science and Computer Engineering

Department of Physics

University of Arkansas

https://cviu.uark.edu/

Email: khoaluu@uark.edu

Department of Physics

University of Arkansas

https://cviu.uark.edu/

Email: khoaluu@uark.edu

Classical neural network algorithms are computationally
expensive. For example, in image classification, representing an image pixel by
pixel using classical information requires an enormous amount of computational
memory resources. Hence, exploring methods to represent images in a different
paradigm of information is important. We proposed a parameter encoding scheme for defining and
training neural networks in quantum information based on time evolution
of quantum spaces.

Differentiating between a classical neural network and a variational
quantum circuit

Schematic of the Variational Quantum circuit used. Every layer is defined as a series of rotation gates in the x and y directions. Every qubit is linked to one other using CNOT gates.

Clustering problems are computationally expensive, especially for large datasets. In addition, it
requires a significant amount of computational resource and time to solve in the typical computer.
Meanwhile, quantum computing can perform calculations exponentially faster than classical computer.
Also, it is suitable for solving complex optimization and searching problems. By this reason, quantum
computing comes in as a potential solution to accelerate clustering algorithms and improve their
performance.

By this reasons, we prose a novel unsupervised clustering framework ultilizing quantum computer. In
particular, we formuate cluster as an optimization problem and then leverage quantum computer for
speedup clustering process.

The Vehicle Routing Problem (VPR) is to find the best routs for a fleet of vehicles to start from and
return to a depot supplying the demand of all customers by visiting them once. The objective of this
problem is to minimize the total cost of travel with the contraint of vehicles capacity.

In quantum machine field, detecting two-dimensional (2D) materials in Silicon chips is one of the most
critical
problems. It is considered as one of bottlenecks in quantum research because of time and labor
consumptions spent on finding a potential flake that might be useful. This progress takes hours to
finish without any warranty that detected flakes being helpful. In order to speedup, reduce cost
and efforts of this progress, we leverage computer vision and AI to build an end-to-end system for
automatically identifying potential flakes and exploring their charactersitics (e.g thickness).

We provide a flexible and generalized solution for 2D quantum crystals identification running on
realtime with high accuracy. The algorithm
is able to work with any kind of flakes (e.g hBN, Graphine, etc),
hardware and environmental settings. It will help to reduces time and labor consumption in research of
quantum technologies.

The cloud-based system overall

Demostration

Dr. Khoa Luu | Dr. Hugh Churchill |

Assistant Professor (Point of Contact) |
Professor |

khoaluu@uark.edu | churchill@uark.edu |

Xuan Bac Nguyen | James Holidays |

Ph.D. Student | Ph.D. Student |

xnguyen@uark.edu | jbhollid@uark.edu |

Apoorva Bisht | Jordan Simpson | Benjamin Thompson |

Honors Student | Honors Student | Honors Student |

abisht@uark.edu | jcs049@uark.edu | bct019@uark.edu |

Xuan Bac Nguyen, Apoorva Bisht, Hugh Churchill, Khoa Luu

Under review of the IEEE International Conference in Image Processing. 2022.

@article{Nguyen2022TwoDimensionalQM, title={Two-Dimensional Quantum Material Identification via Self-Attention and Soft-labeling in Deep Learning}, author={Xuan-Bac Nguyen and Apoorva Bisht and Hugh Churchill and Khoa Luu}, journal={ArXiv}, year={2022}, volume={abs/2205.15948} }

Dendukuri, Aditya, Blake Keeling, Arash Fereidouni, Joshua Burbridge, Khoa Luu, and Hugh Churchill

In Proceedings of Quantum Techniques in Machine Learning. 2019

@article{dendukuri2019defining, title={Defining quantum neural networks via quantum time evolution}, author={Dendukuri, Aditya and Keeling, Blake and Fereidouni, Arash and Burbridge, Joshua and Luu, Khoa and Churchill, Hugh}, journal={arXiv preprint arXiv:1905.10912}, year={2019} }