Image Classification on MNIST (Accuracy and Hardware Efficiency)
97.21Accuracy[16]
Evaluation results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| [16]Year=2025, Learning rule=Optimized AL, Neuron type=IF, Weight bw [bit]=8 or 16, Neuron bw [bit]=13 or 21, Platform=Zynq-7045, Architecture=784-512-1002026.05 | 97.21 | 100 | 398 | 0.467 | 0.39 | 17,578 | 3,877 | 0 | 137.5 | |
| [17]Year=2022, Learning rule=Triple Brain, Neuron type=LIF, Weight bw [bit]=16, Neuron bw [bit]=24, Platform=Zynq-7045, Architecture=784-2562026.05 | 95.1 | 250 | 938 | 0.74 | 0.7 | 10,052 | 8,505 | 32 | 131 | |
| Spiker-LLYear=This work, Learning rule=STSF, Neuron type=LIF, Weight bw [bit]=16, Neuron bw [bit]=16, Platform=Pynq Z2, Architecture=784-200-102026.05 | 92 | 90 | 509 | 0.12 | 0.061 | 13,312 | 6,144 | 0 | 91.5 | |
| [18]Year=2024, Learning rule=PLR, Neuron type=LIF, Weight bw [bit]=8, Neuron bw [bit]=8, Platform=Zynq-7045, Architecture=784-2562026.05 | 90.19 | 250 | 637 | — | — | 6,033 | 1,747 | 0 | 57 | |
| Spiker-LL (8-bits)Year=This work, Learning rule=STSF, Neuron type=LIF, Weight bw [bit]=8, Neuron bw [bit]=8, Platform=Pynq Z2, Architecture=784-200-102026.05 | 90 | 90 | 326 | 0.12 | 0.039 | 8,459 | 4,429 | 0 | 46 |