---
library_name: qiskit
tags:
  - quantum
  - qcnn
  - nisq
  - ibm-quantum
  - variational-quantum-algorithm
license: apache-2.0
---

# Nighthawk-QCNN
![night](https://cdn-uploads.huggingface.co/production/uploads/67329d3f69fded92d56ab41a/Knx2N1lGc6flPfK2mSeQy.jpeg)
**96-qubit Quantum Convolutional Neural Network (QCNN)**

Trained end-to-end on real IBM Quantum Heron r2/r3 hardware

(backend: ibm_fez/ibm_kingston) on February 4, 2026.

## Task
Binary classification of parity of random Pauli-X excitations in 1D cluster state  
(0 — even number → trivial state, 1 — odd number → non-trivial).

## Technical Details

- **Qubits**: 96 (actively used in ansatz + preparation)
- **Architecture**: QCNN with 3 layers (conv → pool → conv → pool → conv → readout)
- **Convolution operator**: 4-parameter 2-qubit block (RY, RZ, CZ), shared parameters
- **Pooling**: static (measure + CZ, no conditional X due to compiler limitations)
- **Readout**: Z-probability on final qubit → MSE loss
- **Trainable parameters**: 72 (8 per layer × 3)
- **Dataset**: 24 samples (on-the-fly generation)
- **Shots per evaluation**: 384
- **Optimizer**: SPSA, 12 iterations
- **Final loss (MSE)**: 0.2704 (after 36 evaluations)
- **QPU time**: ~7 minutes (IBM Heron r2/r3)
- **Backend**: ibm_fez (156 qubits, heavy-hex lattice, tunable couplers)

## Training Convergence

![loss_curve](https://cdn-uploads.huggingface.co/production/uploads/67329d3f69fded92d56ab41a/LDHkVXtixkQm8-ifEBvFv.jpeg)
MSE loss starts at ~0.268, dips to ~0.243 around evaluation 1.0, then rises again due to noise accumulation.

| Run | Qubits | Samples | Shots | Iterations | Final Loss | QPU Time |
|-----|--------|---------|-------|------------|------------|----------|
| 1   | 96     | 16      | 256   | 8          | 0.29       | ~2 min   |
| 2   | 96     | 24      | 384   | 12         | 0.2704     | ~7 min   |



## Repository Files

- `Nighthawk.npy` — trained parameters (72 values)
- `qcnn.qasm` — QASM3 description of the ansatz (parameter-free)
- `results.csv` — final training metrics
- `training_log.txt` — full log of loss evaluations and transpilation
- `requirements.txt` — dependencies for reproduction

![nighthawk banner](https://cdn-uploads.huggingface.co/production/uploads/67329d3f69fded92d56ab41a/nJQdXnlVcCaY-y4uFwjQA.png)

## Usage / Inference

```python
from qiskit import qasm3
import numpy as np

# Load model
theta = np.load("Nighthawk.npy")
qcnn = qasm3.loads(open("qcnn.qasm").read())
qcnn.assign_parameters(theta)

print("Model loaded. Number of parameters:", len(theta))
# Next: compose with preparation circuit + run via Sampler 
```

## Notes

- Proof-of-concept for scaling QCNN on NISQ hardware in 2026.
- Loss near random guess (0.25) due to high noise on Heron r2 — typical for NISQ.
- **Why better results expected on ibm_miami (Nighthawk r1)**:
  - Square lattice topology (vs heavy-hex on Heron r2) → much better natural locality for convolutional layers
  - Higher CLOPS and lower gate errors → deeper circuits with less decoherence
  - Improved connectivity → fewer SWAPs during transpilation → lower overall error accumulation
  - Expected: noticeably lower final loss and higher effective classification accuracy
- Improvements: more shots, error mitigation (twirling/M3), run on Nighthawk (square lattice).

<div align="center">

**Pro Mundi Vita**

</div>