LLY-DML: Differentiable Machine Learning

LLY-DML is a core component of the LILY Project, focusing on developing and optimizing quantum circuits with differentiable machine learning techniques. This project enables researchers and developers to experiment with quantum-enhanced models in a user-friendly and accessible environment.

---

Features

• Optimized Quantum Circuits: Tools for creating and refining quantum algorithms using differentiable optimization techniques.
• Multiple Optimizers: Various optimization algorithms (Adam, SGD, RMSProp, etc.) for different training scenarios.
• Cross-Training: Training of multiple activation matrices with random selection for robust quantum state preparation.
• Automated Reporting: Generates PDF reports with training results and performance metrics.
• Community Collaboration: Open for contributions and discussions to improve and expand the platform.
• Seamless Integration: Available through the LILY QML platform, providing easy access to resources and tools.

---

Quick Links

• 🌐 Website: LILY-QML Platform
• 📚 Documentation: LLY-DML Wiki
• 💬 Discussions: GitHub Discussions
• 📧 Contact: info@lilyqml.de

How to Get Started

1. Clone the repository:

   git clone https://github.com/LILY-QML/LLY-DML.git
   cd LLY-DML
   

2. Install dependencies:

   pip install -r requirements.txt
   

   For development and testing, also install the development dependencies:

   pip install -r requirements-dev.txt
   

3. Run the application:

   python dml/main.py
   

4. Run the tests:

   python dml/test.py
   

For more detailed instructions, refer to the Wiki.

Models

LLY-DML provides pre-built models in the models directory:

LLY-DML-M1

A demonstration model for quantum state classification. This model takes input matrices and classifies them to specific quantum states using the DML framework.

To use this model:

cd models/LLY-DML-M1
python start.py train  # Train the model
python start.py run    # Run the model with input matrices

See the LLY-DML-M1 README for more details.

---

Contributors

Core Team

Role	Name	Links
Project Lead	Leon Kaiser	ORCID, GitHub
Supporting Contributors	Eileen Kühn	GitHub, KIT Profile
Supporting Contributors	Max Kühn	GitHub

Other Contributors

Contributor	Role	Contribution
Clausia	Support in Development	General development support
MrGilli	Support in Quplexity DML Version	Quplexity DML Development
Supercabb	Support in Code Development	Codebase contributions
Userlenn	Support in Code Development	Codebase contributions

---

Public Collaboration

We invite everyone to contribute to LLY-DML. Here's how you can help:

• Discussions: Share your ideas or ask questions in our GitHub Discussions.
• Issues: Report bugs or request features in the Issues section.
• Wiki: Explore or expand our Wiki documentation.

---

License

This project is licensed under the MIT License. See the LICENSE file for details.