Away from the common datasets of Iris or wine, let's say we have dataset of 3 classes and this data is non-separable. How by any way to increase its percentage of correct classification samples...for example from 50% to 80 or 90%?
Asked
Active
Viewed 885 times
1 Answers
2
Your Question is way to vague.
If your data is non-separable, there is no way to separate them. Given the data, the classes are the same.
Maybe you are trying to separate them with linear model and they aren't linear-separable? So you need a non-linear classification like a SVM with non-linear kernel.
Felix S.
- 126
- 4