Are there any research/paper on the relationship between the number of documents for training and the classification performance using support vector machine?


1 Answer 1


In general, in order to achieve better classification results, your database should not contain less than 40 inputs (where you will take 40% for training). It is because if you have less inputs you will have redundancy among your results and you should have constant results in order to prove your hypothesis.

These links contain number of SVM papers:




Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.