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.

vn4

Submitted by Vladimir Nikulin

vn4

Dataset Balanced Error Area Under Curve  
Train Valid Test Train Valid Test
ada 0.1769 0.1901 0.1848 0.8153 0.8038 0.7966 agnostic
gina 0 0 0.0503 1 1 0.9507 agnostic
hiva 0.1935 0.1938 0.3145 0.919 0.8766 0.7562 agnostic
nova 0.0004 0 0.0601 1 1 0.9469 agnostic
sylva 0.0002 0.0004 0.0096 1 1 0.9933 agnostic
Overall 0.0742 0.0769 0.1239 0.9469 0.9361 0.8888 agnostic

This entry is a complete agnostic learning entry.