Skip to content

Latest commit

 

History

History
61 lines (40 loc) · 3.93 KB

README.md

File metadata and controls

61 lines (40 loc) · 3.93 KB
Raw

QML-for-Conspicuity-Detection-in-Production

Womanium Quantum+AI 2024 Projects

Please review the participation guidelines here before starting the project.

Do NOT delete/ edit the format of this read.me file.

Include all necessary information only as per the given format.

Project Information:

Team Size:

  • Maximum team size = 2
  • While individual participation is also welcome, we highly recommend team participation :)

Eligibility:

  • All nationalities, genders, and age groups are welcome to participate in the projects.
  • All team participants must be enrolled in Womanium Quantum+AI 2024.
  • Everyone is eligible to participate in this project and win Womanium grants.
  • All successful project submissions earn the Womanium Project Certificate.
  • Best participants win Womanium QSL fellowships with Fraunhofer ITWM. Please review the eligibility criteria for QSL fellowships in the project description below.

Project Description:

  • Click here to view the project description.
  • YouTube recording of the project description - link

Project Submission:

All information in this section will be considered for project submission and judging.

Ensure your repository is public and submitted by August 9, 2024, 23:59pm US ET.

Ensure your repository does not contain any personal or team tokens/access information to access backends. Ensure your repository does not contain any third-party intellectual property (logos, company names, copied literature, or code). Any resources used must be open source or appropriately referenced.

Team Information:

Team Member 1:

  • Full Name: Mohammadreza Khodajou Masouleh
  • Womanium Program Enrollment ID (see Welcome Email, format- WQ24-xxxxxxxxxxxxxxx): WQ24-Ze8BOdkWw7j6HtQ

Team Member 2:

  • Full Name: Hao Mack Yang Li
  • Womanium Program Enrollment ID (see Welcome Email, format- WQ24-xxxxxxxxxxxxxxx): WQ24-FCtfbMgvc1p1r6x

Project Solution:

Include a comprehensive summary of all important information about your project solution here.

A variational circuit algorithm is used to fit the sine graph given a small number of samples due to the trigonometric nature of the RX gate. In addition, we have located and intend to explore an alternative, advanced method of fitting the sine graph (by solving a differential equation via the somewhat unknown capacity of QSVMs for regression tasks) in the future. If one models the Sine function as the solution to the second order differential equation f''(x) = -f(x) with the boundary conditions f(0) = 0, f'(0) = 1, one can explore the options proposed by the mentioned reference for fitting this function. Of course, there may be limitations but for certain function with some properties, this method seems reliable.

The solution for the weld problem is to implement a customizable Keras quanvolutional network, augmented with Nvidia cuQuantum GPU acceleration to implement a quanvolutional neural network. The quanvolutional neural network convolves the image with a size $K$ square kernel to produce $L$ channels, while downscaling the image by a factor of $K$. The circuit associated with the quanvolutional network (the "quanvolutional circuit") is adjustable and can create families of quantum circuits that vary in the number of inputs (subject to a determinate state preparation) followed by random gates. Each pixel convoluted is converted into the measurements of a quanvolutional circuit run.

Project Presentation Deck:

Upload/ Link a 3min. presentation deck here.

Presentation slides (Google Docs)

See project presentation guidelines here