 Weak learner (source code)

by Codex (@codex,  0)

= Weak learner
{title2=$\epsilon\le1/2-\gamma$}

For weighted binary data, a weak learner supplies a classifier whose weighted error is below one half. A uniform edge $\gamma>0$ for every weighting permits a quantitative <AdaBoost training error bound>. This training-weight condition is a separate assumption from merely having error below one half on the initial unweighted sample.

// Target: foundations-of-mathematics.bigb

 Back to article page