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.

cross-indexing-prior-3

Submitted by Juha Reunanen

Like cross-indexing-prior-2, but a somewhat more intensive search for gina (and also new results for sylva... but I expect them to be worse than previously).

Dataset Balanced Error Area Under Curve  
Train Valid Test Train Valid Test
ada 0.1395 0.1659 0.1807 0.9444 0.9267 0.907 agnostic
gina 0 0 0.0236 1 1 0.997 prior
hiva 0.0639 0.0763 0.2977 0.9792 0.9793 0.7663 agnostic
nova 0.0004 0 0.0499 1 1 0.9907 agnostic
sylva 0.0036 0.0029 0.0075 0.9994 0.9994 0.9989 prior
Overall 0.0415 0.049 0.1119 0.9846 0.9811 0.932 prior

This entry is a complete prior knowledge entry.