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.

RF-CLOP

Submitted by H. Jair Escalante

Random forest implementation in CLOP

Dataset Balanced Error Area Under Curve  
Train Valid Test Train Valid Test
ada 0.0964 0.1132 0.2363 0.9894 0.9871 0.9029 agnostic
gina 0 0 0.0553 1 1 0.9871 agnostic
hiva 0.0185 0.0357 0.387 0.9999 1 0.7749 agnostic
nova 0.007 0 0.1033 1 1 0.9756 agnostic
sylva 0 0 0.0378 1 1 0.9988 agnostic
Overall 0.0244 0.0298 0.1639 0.9979 0.9974 0.9279 agnostic

This entry is a complete agnostic learning entry.