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.

TMK

Submitted by The Machine

TMK 2nd trial
B = 1
S = 0.5
LR

Dataset Balanced Error Area Under Curve  
Train Valid Test Train Valid Test
ada 0.1721 0.198 0.1793 0.9146 0.8823 0.9051 agnostic
gina 0.0174 0.0731 0.0702 0.9989 0.9888 0.9796 agnostic
hiva 0.1137 0.2894 0.2905 0.9623 0.7952 0.7672 agnostic
nova 0.1209 0.154 0.1417 0.9605 0.9357 0.9413 agnostic
sylva 0.0037 0.0111 0.0072 0.9997 0.9991 0.9988 agnostic
Overall 0.0856 0.1451 0.1378 0.9672 0.9202 0.9184 agnostic

This entry is a complete agnostic learning entry.