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.

vrs4

Submitted by Vladimir Nikulin

version4

Dataset Balanced Error Area Under Curve  
Train Valid Test Train Valid Test
ada 0.1839 0.1934 0.1841 0.809 0.7921 0.7966 agnostic
gina 0 0 0.0542 1 1 0.9467 agnostic
hiva 0.1701 0.1776 0.3089 0.9282 0.8842 0.7536 agnostic
nova 0 0 0.0835 1 1 0.932 agnostic
sylva 0.013 0.0156 0.017 0.9794 0.9742 0.973 agnostic
Overall 0.0734 0.0773 0.1295 0.9433 0.9301 0.8804 agnostic

This entry is a complete agnostic learning entry.