Table 6.
Comparison of the SNNs classification accuracies on MNIST, N-MNIST, and CIFAR-10 datasets.
| Model | Learning method |
Accuracy (MNIST) |
Accuracy (N-MNIST) |
Accuracy (CIFAR-10) |
|---|---|---|---|---|
| Hunsberger and Eliasmith (2015) | Offline learning, conversion | 98.37% | – | 82.95% |
| Esser et al. (2016) | Offline learning, conversion | – | – | 89.32% |
| Diehl et al. (2016) | Offline learning, conversion | 99.10% | – | – |
| Rueckauer et al. (2017) | Offline learning, conversion | 99.44% | – | 88.82% |
| Sengupta et al. (2019) | Offline learning, conversion | – | – | 91.55% |
| Kheradpisheh et al. (2016) | Layerwise STDP + offline SVM classifier | 98.40% | – | – |
| Panda and Roy (2016) | Spike-based autoencoder | 99.08% | – | 70.16% |
| Lee et al. (2016) | Spike-based BP | 99.31% | 98.74% | – |
| Wu et al. (2018b) | Spike-based BP | 99.42% | 98.78% | 50.70% |
| Lee et al. (2018) | STDP-based pretraining + spike-based BP | 99.28% | – | – |
| Jin et al. (2018) | Spike-based BP | 99.49% | 98.88% | – |
| Wu et al. (2018a) | Spike-based BP | – | 99.53% | 90.53% |
| This work | Spike-based BP | 99.59% | 99.09% | 90.95% |