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.

linear_SVM_kernel_GentleBoost

Submitted by ebozkurt

linear_SVM_kernel_GentleBoost

Dataset Balanced Error Area Under Curve  
Train Valid Test Train Valid Test
ada 0.2083 0.2524 0.2101 0.8754 0.8412 0.8709 agnostic
gina 0.0285 0.14 0.1708 0.9938 0.9153 0.9109 agnostic
hiva 0.1322 0.344 0.326 0.9872 0.7338 0.7313 agnostic
nova 0.0512 0.128 0.1052 0.9976 0.9578 0.9698 agnostic
sylva 0.0089 0.0119 0.0137 0.9997 0.9985 0.9978 agnostic
Overall 0.0858 0.1753 0.1652 0.9707 0.8893 0.8961 agnostic

This entry is a complete agnostic learning entry.