QML-HCS is a research-grade framework for constructing, simulating, and analyzing quantum-inspired machine learning architectures with hypercausal feedback mechanisms. It integrates deterministic computation with causal inference and quantum-like superposition principles to explore emerging paradigms in Quantum Machine Learning (QML) and Causal Systems Theory.
Rather than assuming stationary data distributions or fixed causal structures, QML-HCS is designed to operate in non-stationary environments, where data distributions drift over time and models must adapt continuously. The framework enables the study of feedback-driven learning, causal stability, and coherent state evolution under concept drift, without relying on full retraining or static causal assumptions.
QML-HCS is intended for researchers, engineers, and advanced practitioners working in quantum machine learning, causal modeling, hybrid quantum–classical computation, and adaptive learning systems operating in dynamic or drift-dominated environments.
This framework supports research across the following areas:
- Quantum Machine Learning: Development of quantum-inspired learning architectures.
- Causal Dynamics and Feedback Modeling: Formalization of recursive multi-branch causal systems.
- Hybrid Quantum–Classical Computation: Simulation of efficient causal propagation in hybrid systems.
- Counterfactual Simulation: Modeling systems capable of evaluating alternative causal scenarios.
- Algorithmic Benchmarking: Studying quantum-efficient learning and reasoning processes on classical hardware.
- Hypercausal Feedback Modeling: Implement layered feedback systems capable of multi-directional causal propagation.
- Quantum-Inspired Efficiency: Apply principles of superposition and entanglement to reduce computational cost.
- Deterministic–Stochastic Integration: Provide configurable backends for deterministic, probabilistic, and mixed causal engines.
- Scientific Transparency: Ensure reproducibility and open experimentation through standardized interfaces.
- Scalability and Extensibility: Support modular expansion for backends, loss functions, and causal evaluators.
Install the package directly from PyPI:
pip install qml-hcsInstall a specific version:
pip install qml-hcs==0.2.0Verify installation:
python -c "import qmlhc; print(qmlhc.__version__)"This mode is recommended for research and production environments where the source code remains static but full access to all APIs and modules is required.
To verify installation, execute the minimal example:
qmlhc-demoor run directly as a module:
python -m qmlhc.examples.ex_minimal_core_demoExpected output (abridged):
=== Minimal Core Demo ===
output_dim (D): 3
branches (K): 3
...
HCModel.forward() matches single-node result ✔
Refer to the Getting Started Guide for further instructions.
The repository provides several scientifically oriented demonstrations:
- Minimal hypercausal core operation
- Depth-dependent evaluation of feedback models
- Quantum-inspired benchmarking and stability testing
- Training with callback telemetry and adaptive losses
- Coherence and consistency experiments under stochastic variation
All examples are documented in the Examples Section.
QML-HCS serves as a research platform for the theoretical and experimental study of quantum-inspired machine learning.
It facilitates investigations in:
- Quantum-efficient learning architectures
- Simulation of adaptive feedback systems
- Analysis of causal consistency and information stability
- Hybrid quantum–classical training methodologies
- Exploration of hypercausal structures for predictive and inferential modeling
By providing a deterministic yet quantum-compatible environment, QML-HCS enables the testing of emerging theories in quantum-causal computation without the need for specialized quantum hardware.
Contributions are welcome.
Researchers and developers can improve QML-HCS by adding new modules, extending the documentation, or enhancing the quantum-hypercausal backends.
- Fork the repository and create a feature branch.
- Follow PEP 8 conventions and maintain typing annotations.
- Ensure test coverage remains above 75%.
- Provide detailed documentation and minimal runnable examples.
- Submit a well-described pull request for review.
Further details are available in the Contributing Section.
To execute the test suite:
pytest -vTo build documentation locally:
sphinx-build -E -a -b html docs/ docs/_build/htmlView the generated site by opening:
docs/_build/html/index.html
For bug reports or feature suggestions, please use the official issue tracker:
When reporting, include:
- Operating system and Python version
- Steps to reproduce
- Logs or traceback if available
QML-HCS is part of the NeureonMindFlux Research Lab initiative to formalize quantum–causal computational frameworks.
It seeks to unify Quantum Machine Learning, Causal Inference, and Deterministic Modeling into a single, reproducible platform for scientific investigation and applied experimentation.
If you use QML-HCS in your research, please cite the following work
👉 View the preprint on arXiv
@misc{mozo2025qmlhcshypercausalquantummachine,
title={QML-HCS: A Hypercausal Quantum Machine Learning Framework for Non-Stationary Environments},
author={Hector E Mozo},
year={2025},
eprint={2511.17624},
archivePrefix={arXiv},
primaryClass={cs.LG},
url={https://arxiv.org/abs/2511.17624},
}Developed under the NeureonMindFlux Research Initiative in quantum-inspired and hypercausal computation.
The project benefits from ongoing collaboration and peer feedback within the open scientific community.
Full documentation is available here:
QML-HCS Official Documentation
For inquiries, collaboration proposals, or research-related communication regarding QML-HCS, please use the following contact:
Email: contact@neureonmindfluxlab.org
QML-HCS — advancing research in Quantum Machine Learning with Hypercausal Feedback Systems.