Quantum machine learning · Apache-2.0
Quantum memory, classical learning.
QMANN combines classical neural networks with quantum memory operations to push learning capacity past what classical models alone can reach. The reference implementation provides practical quantum-inspired algorithms suitable for near-term NISQ devices, with three reproducible modes — Theoretical, Simulation, and Hardware.
Unlimited (ideal quantum computer)
Up to 20 (with noise modelling)
4–12 (NISQ-bounded)
3
Reproducible modes
20
Qubits in simulation
4–12
Qubits on hardware
Apache-2.0
Open licence
Modes
Pick the mode, not the marketing.
Most QML libraries hide the cost surface and the noise model. QMANN exposes both, and ships three explicit modes so you always know what your run actually means.
Simulation mode
Algorithm validation, development, education, reproducible research
Qubits
Up to 20
Noise
Configurable
When to use
- Iterating on a model where every shot needs to be reproducible
- Pre-flight checks before paying for hardware shots
- Education and CI — anyone can re-run the same code on the same noise model
Active config
| qubits | ≤ 20 |
| noise_model | depolarising / amplitude / readout (configurable) |
| shots | configurable, no rate limit |
| cost | $0.00 (compute only) |
| purpose | development / validation |
from qmann.config import SIMULATION_VALIDATION
from qmann import QMANN, QMANNTrainer
validate_experimental_setup(SIMULATION_VALIDATION)
model = QMANN(
input_dim=10,
hidden_dim=64,
output_dim=3,
memory_capacity=32,
max_qubits=8, # simulation upper bound
)
trainer = QMANNTrainer(model)
trainer.train_epoch(X_train, y_train)Switch modes above to see how qubit budget, noise model, cost, and example code change.
Core
Four components, hybrid by design.
Q-Matrix
Quantum memory layer with entangled qubit registers.
Quantum-LSTM
Hybrid controller with parameterised quantum circuits.
Energy-optimal protocols
Advanced error mitigation and measurement strategies.
Real-world applications
Healthcare, industrial IoT, autonomous systems modules.
2025 techniques
Citations, not vibes.
Every technique below maps to a published reference. Pull the paper, read the section, then run the code.
Quantum LSTM with segment processing
QSegRNN-style segment-based quantum recurrent neural networks. Quantum gates for LSTM operations, hybrid memory cells, enhanced temporal pattern recognition.
EPJ Quantum Technology · March 2025
QAOA with warm-start adaptive bias
Conditional diffusion-based parameter generation. Classical solution warm-start, adaptive bias correction. Faster convergence with reduced optimisation overhead.
Physical Review · 2025; EPJ Quantum Technology · August 2025
Grover dynamics optimisation
Grover-inspired amplitude amplification for optimisation problems. O(√N) speedup for unstructured search with adaptive oracle construction.
Cornell Lawler Research · January 2025
Quantum-enhanced transformers
Quantum-classical attention integration. Multi-head quantum attention, entanglement-based correlations, configurable quantum attention ratio (0–100%).
arXiv:2504.00068 · arXiv:2501.15630
Circuit-noise-resilient virtual distillation
Enhanced virtual distillation with noise resilience. Multiple virtual copies, adaptive thresholds, maintains effectiveness with imperfect gates.
Communications Physics · October 2024
Learning-based error mitigation
ML models for quantum error prediction and correction. Neural network error models, adaptive strategies, real-time error prediction and correction.
Recent QEM literature · 2025
Applications
Five sectors with concrete pipelines.
| Sector | Example pipelines |
|---|---|
| Finance | QAOA portfolio optimisation, fraud detection on transaction streams, market prediction with quantum LSTMs, quantum-enhanced risk modelling and stress testing. |
| Drug discovery | Quantum transformers for molecular property prediction, drug-target binding affinity, Grover-dynamics molecule generation, ADMET safety prediction. |
| Materials science | Quantum property prediction, adaptive-VQE crystal structure refinement, battery material design, catalyst design via quantum simulation. |
| Healthcare | Pattern recognition for diagnosis, optimisation for personalised medicine, protein folding via quantum simulation, clinical-trial patient matching. |
| Industrial | Quantum anomaly detection for predictive maintenance, classifiers for defect detection, QAOA for logistics, quantum simulation for chemical processes. |
Quick start
Pick a mode. Run an example.
$ git clone https://github.com/neuraparse/QMANN.git $ cd QMANN $ pip install -e . # 🔬 Theoretical mode (FREE) $ python examples/01_theoretical_mode.py # 💻 Simulation mode (FREE) $ python examples/02_simulation_mode.py # ⚛️ Hardware mode (PAID — estimate first!) $ python scripts/estimate_hardware_costs.py --qubits 6 --shots 1000 $ python examples/03_hardware_mode.py
In the stack
QMANN compiles through qmesh.
When you target hardware, QMANN circuits flow through qmesh for IR lowering, error mitigation, and ed25519-signed run manifests. The same provenance chain that satisfies regulated industries also gives ML researchers fully reproducible benchmarks.