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.

Finale

Submitted by H. Jair Escalante

Finale 1

Dataset Balanced Error Area Under Curve  
Train Valid Test Train Valid Test
ada 0.1834 0.2063 0.1924 0.9026 0.8703 0.8988 agnostic
gina 0 0.0413 0.0577 1 0.9948 0.985 agnostic
hiva 0.1228 0.3251 0.2922 0.9594 0.7705 0.7654 agnostic
nova 0.0004 0.048 0.0508 1 0.9958 0.9896 agnostic
sylva 0.0079 0.0107 0.0115 0.9991 0.999 0.9983 agnostic
Overall 0.0629 0.1263 0.1209 0.9722 0.9261 0.9274 agnostic

This entry is a Model Selection Game entry.