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 |
---|---|---|---|---|
ReLU 6X | 84.40 | a | 5.55 | 161.41 |
ReLU 3X | 81.68 | b | 1.84 | 58.91 |
Maxout 3-2 | 78.74 | c | 33.41 | 813.15 |
Maxout 3-1 | 78.60 | c | 15.83 | 538.38 |
ReLU 2X | 78.34 | cd | 7.83 | 309.25 |
Maxout 2-1 | 78.08 | cd | 9.90 | 410.16 |
Maxout 6-1 | 77.71 | d | 19.21 | 723.22 |
ReLU | 76.42 | e | 3.70 | 166.72 |
Tanh | 76.19 | e | 3.52 | 152.22 |
LReLU | 76.14 | e | 6.43 | 291.52 |
SeLU | 74.78 | f | 6.13 | 254.32 |