AI-In-Quantum-Technologies

AI in Quantum Technologies

“Do you really believe the moon is only there when you look at it?” — Albert Einstein

About This Repository

This repository is the living digital companion to the textbook “AI in Quantum Technologies: Theory, Applications, Practice, and Society” (DaScient Press Ltd., 2026). It provides a hands‑on, code‑first journey through the rapidly evolving intersection of artificial intelligence and quantum science. Inside you will find:

Quick Start

Local Installation

# Clone the repository
git clone https://github.com/DaScient/ai-in-quantum.git
cd ai-in-quantum

# Create and activate conda environment
conda create -n ai-quantum python=3.11
conda activate ai-quantum

# Install the package with all quantum and ML dependencies
pip install -e .[all]

# Launch Jupyter Lab
jupyter lab

Docker Quick Start

docker-compose up -d
# API available at http://localhost:8000
# Jupyter at http://localhost:8888 (token: quantum)
# MLflow tracking server at http://localhost:5000

Textbook Chapters

The textbook is structured into eight parts, each building the conceptual and practical machinery required to apply AI across the quantum technology landscape. Every chapter includes a fully executable notebook that can be run locally or opened directly in Google Colab.

Part Chapter Notebook
I: Foundations 1. Quantum Mechanics as Information Science Open In Colab
  2. Artificial Intelligence: Paradigms for Quantum Discovery Open In Colab
  3. Mathematical and Computational Toolbox Open In Colab
II: Quantum Data Across Scales 4. Representing Quantum States and Processes Open In Colab
  5. Datasets from Quantum Experiments Open In Colab
  6. Noise, Decoherence, and Real‑World Imperfections Open In Colab
III: AI for Quantum Devices 7. Quantum Optimal Control Open In Colab
  8. Quantum Error Correction & Mitigation Open In Colab
  9. Quantum Metrology & Sensing Open In Colab
IV: AI for Quantum Matter 10. Quantum Chemistry & Molecular Design Open In Colab
  11. Quantum Materials Discovery Open In Colab
  12. Many‑Body Physics & Tensor Networks Open In Colab
V: Quantum Information & Communication 13. Quantum Cryptography & Security Open In Colab
  14. Quantum Networks & Repeaters Open In Colab
  15. Quantum Algorithms & Complexity Open In Colab
VI: Quantum Machine Learning & Hybrid Systems 16. Quantum Machine Learning Fundamentals Open In Colab
  17. Variational Quantum Algorithms Open In Colab
  18. Quantum‑Classical Hybrid Computing Open In Colab
VII: Ethics, Policy, and Societal Impact 19. Ethical Dimensions of Quantum AI Open In Colab
  20. Governance & Standards for Quantum Technologies Open In Colab
  21. Workforce, Equity, and Geopolitics Open In Colab
VIII: Horizons 22. Co‑Evolution of AI and Quantum Hardware Open In Colab
  23. Open Questions and Fundamental Limits Open In Colab
  24. Toward a Quantum‑Native Intelligence Open In Colab

All chapters are then exported to a single .docx file for manuscript processing by DaScient Press, Ltd.

API Endpoints

A production‑ready FastAPI service exposes state‑of‑the‑art AI models tailored to quantum science. The interactive documentation is available at /docs once the server is running.

Endpoint Method Description
/api/v1/quantum/state_tomography POST Reconstruct quantum state from measurement outcomes
/api/v1/quantum/process_tomography POST Characterise unknown quantum processes
/api/v1/quantum/optimal_control POST Generate optimal pulse sequences for gate operations
/api/v1/quantum/error_decode POST Decode syndrome measurements for error correction
/api/v1/quantum/circuit_optimize POST Compress and optimise quantum circuit depth
/api/v1/qchem/ground_state POST Predict molecular ground state energies
/api/v1/qchem/excited_states POST Compute optical spectra using ML‑enhanced methods
/api/v1/materials/crystal_generation POST Inverse design of crystal structures with desired properties
/api/v1/materials/superconductor POST Predict superconducting critical temperatures
/api/v1/qml/kernel POST Compute quantum kernel matrices for classification
/api/v1/qml/train POST Train a hybrid quantum‑classical model
/api/v1/crypto/key_rate POST Estimate secret key rate for QKD protocols
/api/v1/metrology/sensitivity POST Optimise probe states for quantum sensing
/api/v1/simulate/noise_model POST Learn a device noise model from calibration data

Pre-trained Models Available

All models are hosted on Hugging Face under the dascient organisation. They can be loaded with a few lines of code using the transformers, pennylane, or torch ecosystems.

Model Description Parameters Download
Q‑BERT Quantum‑adapted BERT for gate sequence tokenisation 110M Link
ErrorFormer Transformer for surface code error decoding 230M Link
MolQNet Molecular ground state prediction with SE(3) equivariance 340M Link
CrysDiff Diffusion model for crystal structure generation 450M Link
Q‑GPT Generative pre‑trained transformer for quantum circuit synthesis 1.2B Link
SensNet Graph neural network for quantum sensor placement 85M Link
QKD‑Flow Normalising flow for quantum channel parameter estimation 175M Link

Benchmark Datasets

The repository includes ready‑to‑use dataloaders for the following curated datasets. All are pre‑processed and documented in the /datasets directory.

Interactive Learning Paths

In addition to the chapter notebooks, the /tutorials folder contains thematic learning paths that cut across multiple chapters:

  1. “From Bell States to Transformers” – A complete walk‑through of quantum state classification with deep learning.
  2. “Designing a Superconducting Qubit with AI” – Inverse design tutorial using a pre‑trained diffusion model.
  3. “Quantum Error Correction Decoder Challenge” – Build and submit your own ML decoder; leaderboard included.
  4. “Certified Quantum Randomness” – Verify quantum advantage with AI‑powered statistical tests.
  5. “Ethical Audit of a Quantum AI System” – Apply the textbook’s ethics framework to a real API model.

Contributing

We welcome contributions from the global quantum and AI communities. Please see CONTRIBUTING.md for detailed guidelines.

We are especially interested in contributions that:

Citation

@book{tadaya2026aiquantum,
    title     = {AI in Quantum Technologies: Theory, Applications, Practice, and Society},
    author    = {Tadaya, Don D.M.},
    year      = {2026},
    publisher = {DaScient Press},
    series    = {DaScient Intelligence Academy Textbook Series},
    library_no = {178847474773666374859402992856},
    isbn      = {TBD}
}

License

This work is licensed under a Creative Commons Attribution‑NonCommercial‑ShareAlike 4.0 International License. You are free to share and adapt the material under the same terms, provided you give appropriate credit. Commercial licensing (e.g., for corporate training, proprietary product integration) is available — please contact commercial@dascient.com.

Acknowledgments

Contact

This site is open source. Improve this page.