Image Classification on MNIST (test) (Standard Accuracy and Error Reduction)
99.69Test Accuracy (Avg)VGG-5
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| VGG-5Size of Fully Connected Layer=1HL, 512 Neurons, Epoch=100, Parameters=3.646M2020.07 | 99.69 | 99.72 | — | |
| VGG-5 (Spinal FC)Size of Fully Connected Layer=4HL, 128 Neurons Per Layer, Epoch=100, Parameters=3.630M2020.07 | 99.69 | 99.72 | 0 | |
| CNN (Spinal FC)Size of Fully Connected Layer=6HL, 10 Neurons Per Layer, Epoch=8, Parameters=16.05k2020.07 | 98.37 | 98.48 | 16.9 | |
| CNN (Spinal FC)Size of Fully Connected Layer=6HL, 8 Neurons Per Layer, Epoch=8, Parameters=13.82k2020.07 | 98.32 | 98.44 | 14.8 | |
| CNNSize of Fully Connected Layer=1HL, 50 Neurons, Epoch=8, Parameters=21.84k2020.07 | 97.98 | 98.17 | — |