PASCAL Agnostic Learning
vs.
Prior Knowledge
IJCNN07

The challenge is now over. But it remains open for post-challenge submissions!


IMPORTANT: Entries made since February 1st 2007 might be using validation data, now available for training.

svm

Submitted by Joerg Wichard

the last trial, let's see how it works with svm's

Dataset Balanced Error Area Under Curve  
Train Valid Test Train Valid Test
ada 0.1556 0.206 0.1797 0.9282 0.8785 0.9048 agnostic
gina 0.0766 0.098 0.1006 0.9741 0.957 0.9544 agnostic
hiva 0.1568 0.2813 0.3003 0.9245 0.7809 0.7641 agnostic
nova 0.0251 0.108 0.1029 0.9973 0.955 0.9548 agnostic
sylva 0 0.0749 0.0552 1 0.9895 0.9895 agnostic
Overall 0.0828 0.1536 0.1478 0.9648 0.9122 0.9135 agnostic

This entry is a complete agnostic learning entry.