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.

PCBoosting

Submitted by H. Jair Escalante

PCBoosting

Dataset Balanced Error Area Under Curve  
Train Valid Test Train Valid Test
ada 0.1982 0.2186 0.1946 0.8851 0.8583 0.8873 agnostic
gina 0 0.0701 0.0929 1 0.985 0.9656 agnostic
hiva 0.2196 0.3546 0.3315 0.9003 0.7147 0.7422 agnostic
nova 0.0012 0.046 0.0695 1 0.9882 0.9842 agnostic
sylva 0.0079 0.0053 0.0121 0.9991 0.9991 0.9983 agnostic
Overall 0.0854 0.1389 0.1401 0.9569 0.9091 0.9155 agnostic

This entry is a Model Selection Game entry.