Table 2 Experimental environment and model hyperparameter settings.
From: Research on cross-dataset cardiac signal domain generalization and feature interpretability
Configuration | Setting |
|---|---|
GPU | NVIDIA RTX 3090 (24GB) |
CPU | Intel Xeon Gold 6226R |
Memory | 128 GB |
Operating System | Ubuntu 20.04 |
Deep learning framework | PyTorch 2.0 |
Optimizer | AdamW |
Learning rate | \(1 \times 10^{-4}\) |
Batch size | 64 |
Maximum epochs | 50 |
Early stopping | patience = 10 |
Transformer layers | 6 |
Hidden dimension | 256 |
Attention heads | 8 |
Dropout | 0.1 |
\(\lambda _1\) | 0.5 |
\(\lambda _2\) | 0.5 |
