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.

OTMK

Submitted by The Machine

Meta Learning with Boosted Ensembles of Wiener Process Classifier
OTMK Feature Selection

Dataset Balanced Error Area Under Curve  
Train Valid Test Train Valid Test
ada 0.2402 0.2716 0.27 0.9201 0.87 0.9041 agnostic
gina 0.0022 0.0477 0.0637 1 0.9896 0.9815 agnostic
hiva 0.1385 0.251 0.3012 0.9542 0.7992 0.7538 agnostic
nova 0.1135 0.128 0.1305 0.9642 0.9323 0.9419 agnostic
sylva 0.0038 0.0115 0.0074 0.9996 0.9993 0.9987 agnostic
Overall 0.0996 0.1419 0.1545 0.9676 0.9181 0.916 agnostic

This entry is a complete agnostic learning entry.