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.

ffs monoms

Submitted by Chen

work in progress

Dataset Balanced Error Area Under Curve  
Train Valid Test Train Valid Test
ada 0.2026 0.214 0.1975 0.7964 0.7885 0.8015 agnostic
gina 0.0353 0.0538 0.0829 0.9658 0.9446 0.9168 agnostic
hiva 0.0892 0.1571 0.3303 0.9096 0.7741 0.6717 agnostic
nova 0.075 0.128 0.1217 0.9274 0.8539 0.8787 agnostic
sylva 0.0117 0.0073 0.0159 0.989 0.9923 0.9841 agnostic
Overall 0.0828 0.1121 0.1497 0.9177 0.8707 0.8506 agnostic

This entry is a complete agnostic learning entry.