Table 3 Dataset and hyperparemeters specifications. BS batch size, Opt optimizer, LR learning rate.
From: Deep quanvolutional neural networks with enhanced trainability and gradient propagation
Dataset specs | BS | Opt | LR | Quanvolutional layer specs | Postprocessing | ||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
Total classes | Samples/class | Train data | Test data | Â | Â | Â | Encoding | Kernel size | # of qubits | Classical | Quantum |
10 | 200 | 1600 | 400 | 16 | Adam | 0.01 | Angle (RY) | \(2 \times 2\) | 4 | Dense layer (10 neurons) | – |
4 | 200 | 640 | 160 | 16 | Adam | 0.01 | Angle (RY) | \(2 \times 2\) | 4 | – | 10-Qubit circuit (4 measured) |
