Neura Parse

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.

qmann / mode-selector
🔬
TheoreticalFree

Unlimited (ideal quantum computer)

💻
SimulationFree

Up to 20 (with noise modelling)

⚛️
HardwarePaid

4–12 (NISQ-bounded)

Hardware mode runs cost estimator before any shots are submitted.

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.

💻

Algorithm validation, development, education, reproducible research

Up to 20

Configurable

  • 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
qubits≤ 20
noise_modeldepolarising / amplitude / readout (configurable)
shotsconfigurable, no rate limit
cost$0.00 (compute only)
purposedevelopment / validation
qmann / examples / 02_simulation_mode.py
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.

Quantum memory layer with entangled qubit registers.

Hybrid controller with parameterised quantum circuits.

Advanced error mitigation and measurement strategies.

Healthcare, industrial IoT, autonomous systems modules.

Every technique below maps to a published reference. Pull the paper, read the section, then run the code.

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

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-inspired amplitude amplification for optimisation problems. O(√N) speedup for unstructured search with adaptive oracle construction.

Cornell Lawler Research · January 2025

Quantum-classical attention integration. Multi-head quantum attention, entanglement-based correlations, configurable quantum attention ratio (0–100%).

arXiv:2504.00068 · arXiv:2501.15630

Enhanced virtual distillation with noise resilience. Multiple virtual copies, adaptive thresholds, maintains effectiveness with imperfect gates.

Communications Physics · October 2024

ML models for quantum error prediction and correction. Neural network error models, adaptive strategies, real-time error prediction and correction.

Recent QEM literature · 2025

FinanceQAOA portfolio optimisation, fraud detection on transaction streams, market prediction with quantum LSTMs, quantum-enhanced risk modelling and stress testing.
Drug discoveryQuantum transformers for molecular property prediction, drug-target binding affinity, Grover-dynamics molecule generation, ADMET safety prediction.
Materials scienceQuantum property prediction, adaptive-VQE crystal structure refinement, battery material design, catalyst design via quantum simulation.
HealthcarePattern recognition for diagnosis, optimisation for personalised medicine, protein folding via quantum simulation, clinical-trial patient matching.
IndustrialQuantum anomaly detection for predictive maintenance, classifiers for defect detection, QAOA for logistics, quantum simulation for chemical processes.
$ 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

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.