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.

xent cubic lssvm

Submitted by reference

LS-SVM with a normalised inhomogenous cubic kernel. Model selection using scaled conjugate gradient descent, minimising the cross-entropy criterion.

Performance Estimates:

ADA - BER = 0.187986 : AUC = 0.899199

GINA - BER = 0.052681 : AUC = 0.987075

HIVA - BER = 0.310177 : AUC = 0.722855

NOVA - BER = 0.056078 : AUC = 0.985146

SYLVA - BER = 0.011201 : AUC = 0.998760

Dataset Balanced Error Area Under Curve  
Train Valid Test Train Valid Test
ada 0.1644 0.2046 0.1891 0.9219 0.8726 0.8991 agnostic
gina 0 0.0285 0.0471 1 0.9956 0.99 agnostic
hiva 0 0.2838 0.3378 1 0.7444 0.6998 agnostic
nova 0.0004 0.064 0.0543 1 0.9942 0.9887 agnostic
sylva 0.009 0.0061 0.0117 0.9991 0.9989 0.9985 agnostic
Overall 0.0348 0.1174 0.128 0.9842 0.9212 0.9152 agnostic