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.

Intel-GBT-PF-1 (Intel final 4)

Submitted by Vladimir Martyanov

Intel-GBT-PF-1 submitted on 0708011326

Dataset Balanced Error Area Under Curve  
Train Valid Test Train Valid Test
ada 0.1401 0.1626 0.1781 0.8576 0.8491 0.8213 agnostic
gina 0 0 0.0394 1 1 0.961 agnostic
hiva 0.0943 0.0641 0.2908 0.911 0.9421 0.7067 agnostic
nova 0.0182 0.028 0.0833 0.9833 0.9637 0.9165 agnostic
sylva 0.0002 0.0004 0.0109 0.9999 0.9996 0.9891 agnostic
Overall 0.0506 0.051 0.1205 0.9504 0.9509 0.8789 agnostic

This entry is a complete agnostic learning entry.