Table 16 Poor hyperparameter setting detection rate for each method (Batch-Normalized Maxout Network in Network)
From: Effective hyperparameter optimization using Nelder-Mead method in deep learning
Method | Detection rate |
|---|---|
Random search | 0 (±0) |
Bayesian optimization | 0.004943 (±0.001991) |
Coordinate-search method | 0.048941 (±0.054884) |
CMA-ES | 0 (±0) |
Nelder-Mead method | 0 (±0) |