Image Classification on MNIST Large 784-392-196-10 (test)
94.38Reference AccuracyVQ4SNN
Evaluation Results
| Method | Links | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| VQ4SNNDesign=Proposed, Config=L1:d=8 k=2^11 L2:d=8 k=2^11, Network Type=FC-FF-R, Weight bits=8, Memb. Potential bits=15, Spikes time-steps=252026.06 | 94.38 | 92.7 | 33,081 | 14,809 | — | 47.5 | 364 | 1.093 | |
| ModNEFDesign=ModNEF, Network Type=FC-FF, Weight bits=8, Memb. Potential bits=16, Spikes time-steps=1002026.06 | 93.2 | 96.96 | 20,321 | 28,284 | 3 | 113.5 | 336 | 0.904 |