From: Evaluation of maxout activations in deep learning across several big data domains
Activation | Average accuracy (%) | Accuracy HSD | Average 100 batches time (s) | Average 100 batches training time |
---|---|---|---|---|
Maxout 2-1 | 83.19 | a | 11.59 | 983.18 |
Maxout 3-2 | 82.88 | ab | 39.99 | 2839.32 |
ReLU2x | 82.83 | ab | 10.68 | 1299.48 |
Maxout 3-1 | 82.32 | ab | 19.08 | 1619.91 |
Maxout 6-1 | 81.18 | abc | 30.32 | 3219.95 |
LReLU | 80.90 | abc | 8.99 | 1180.16 |
ReLU | 80.72 | abc | 5.05 | 602.98 |
SeLU | 80.29 | bc | 7.87 | 539.84 |
Tanh | 78.88 | c | 5.07 | 487.91 |