| Dataset |
Nearest means |
Naive bayes |
Least squares (on std data, eta=.001, term=.001) |
Hinge loss (on std data, eta=.001, term=.000001) |
| Breast cancer |
15.87 | 7.15 | 7.2 | 4.7 |
| Climate |
15.1 | 21.3 | 50.0 | 49.7 |
| Qsar | 33.43 | 23.54 | 20.9 | 15.8 |
| Ionosphere | 27.97 | 32.39 | 20.3 | 21.1 |
| Micromass | 11.7 | 28.2 | No convergence | 1.2 (five splits) |
| Hill valley (standardized) | 46.8 | 48.2 | 35.4 | 49.0 |