QML-for-Conspicuity-Detection-in-Production

Womanium Quantum+AI 2024 Projects

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.
• Everyone is eligible for Womanium QSL fellowships with Fraunhofer.
• All successful project submissions earn the Womanium Project Certificate.

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: Adriano Lusso

• Email: [email protected]
• Discord ID: AdriLusso#9793
• GitHub ID: AdrianoLusso
• Nationality: Argentina
• Current affiliation: Grupo de Investigación en Lenguajes e Inteligencia Artificial (GILIA), Universidad Nacional del Comahue

Team Member 2: Jalal Naghiyev

• Email: [email protected]
• Discord ID: Jalaln06#5484
• GitHub ID: Jalaln06
• Nationality: Azerbaijan
• Current affiliation: ITMO University

Project Solution:

The repository is structured in 5 main folders, each of them corresponding to each task.

1. a .md file explaining what we learnt during Pennylane tutorials, and a link to the account where we made some of the corresponding code exercises.
2. use the notebook task2.ipynb to see the implementation of a Variational Classifier.
3. use the notebook task3.ipynb to see the implementation of a Quanvolutional Neural Network (QCNN).
4. use the notebook task4.ipynb to see the implementation of a regression model which predicts many trigonometrical functions (not just a simple sine function :D).
5. For the conspicuity detection, we defined two models:
   1. a multi-classification model using a QCNN (inspired in task 3). Here, we focus in classifying each of the six categories independently.
   2. a binary classification model with a Quantum Variational Autoencoder. Here, the categories associated to conspicueties (1 to 5) where considered a unique category, and the good weld the second category. The idea is to diferentiate if the production part is defective or not.

Project Presentation Deck:

(5 minutes presentation, asked in this MD)

https://www.youtube.com/watch?v=QmIbuE2fJMI

(3 minutes presentation, asked by Womanium)

available in this repository