Theory and Modern Applications
From: Path classification by stochastic linear recurrent neural networks
Noise scale | Accuracy | Robustness test accuracies | Ratio | ||||||
---|---|---|---|---|---|---|---|---|---|
NRNN | min | max | avg. | NRNN | min | max | avg. | ||
2 | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100% | 100.00% |
4 | 100% | 88.33% | 98.33% | 94.83% | 100% | 90.00% | 100.00% | 92.83% | 97.89% |
6 | 100% | 73.33% | 90.00% | 79.83% | 100% | 71.67% | 81.67% | 76.67% | 96.03% |