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.

PSMS-SUBSAMPLE-ENSEMBLE-TOP-5

Submitted by H. Jair Escalante

PSMS with subsampling, a ensemble is built with the best 5 particles in the final swatm

Dataset Balanced Error Area Under Curve  
Train Valid Test Train Valid Test
ada 0.1855 0.2077 0.1808 0.906 0.8869 0.9027 agnostic
gina 0.0003 0 0.0409 1 1 0.9923 agnostic
hiva 0.0162 0.0068 0.292 0.9974 0.9979 0.7701 agnostic
nova 0.0004 0.044 0.0511 1 0.997 0.9896 agnostic
sylva 0.0185 0.009 0.0162 0.997 0.9981 0.9973 agnostic
Overall 0.0442 0.0535 0.1162 0.9801 0.976 0.9304 agnostic

This entry is a complete agnostic learning entry.