Results for Exercise Sheet 11 (SVM vs. Naive Bayes)
Please read the instructions below, before adding something to the table!
Add your row to the table below, following the examples already there. Column 2 = percentage of correctly classified documents in the test set, with exactly one digit of precision / the number of documents in the training set that are not classified correctly / the width of the band when taking those mis-classified documents out of the training set (if any). Column 3 = the same for Support Vector Machines without allowing outliers. Column 4 = the same for Support Vector Machines when allowing outliers.
For easier visual reference: the numbers in each of the last three columns are % in test set predicted correctly / # misclassified in training set / band width.
Name |
Naive Bayes |
SVM strict |
SVM with outliers |
Hannah |
??.?% / ?? / ?? |
??.?% / ?? / ?? |
??.?% / ?? / ?? |
Fabian S |
99.3% / 8 / 0.00040 |
100% / 0 / 0.45067 |
98.6% / 15 / 0.75625 |
Nikolaus |
97.1% / 3 / 0.0099 |
95.1% / 0 / 1.06 |
71.2% / 247 / ? |
Jan M |
97.1% / 5 / 2.24 |
96.4% / 0 / 0.95 |
90.4% / 81 / 1.49 |