Table 15 HSD test on maxout, low memory usage activation functions and ReLU2x, 3x and 6x
From: Evaluation of maxout activations in deep learning across several big data domains
Activation | Average accuracy (%) | Accuracy HSD | Average 100 batches training time | Average 100 batches training time HSD |
|---|---|---|---|---|
ReLU 2X, 3X and 6X | 80.22 | a | 229.61 | a |
Maxout 2-1, 3-1, 3-2 and 6-1 | 78.29 | b | 621.18 | b |
ReLU, Tanh, LReLU and SeLU | 75.91 | c | 215.17 | a |