Quantum ML · BCI
QNeuroGen
Quantum-enhanced EEG neural decoding system for mental-state classification.
89.2% accuracy · <50ms latency · 12% above classical baselines
Documented system flow
How QNeuroGen is structured
Select a node to inspect its role.
EEG signals
Brain-signal inputs represent Focused, Relaxed, Excited, and Drowsy states.
Interactive readme
Explore QNeuroGen
A concise, source-backed implementation record with the available project actions.
What is documented
- Classifies Focused, Relaxed, Excited, and Drowsy states from EEG using variational quantum circuits, amplitude embedding, and QFT feature extraction.
- Combines PennyLane and Cirq quantum features with a TensorFlow hybrid quantum-classical neural network.
- Includes a Flask and Docker API pipeline and is described as open-sourced for research use.
Technology used
PennyLaneCirqTensorFlowFlaskDocker
Source: supplied LinkedIn. This is a concise visualization of documented components, not a full internal deployment blueprint.