Review Note
Last Update: 10/08/2023 02:57 PM
Current Deck: EEN100: Theory and exercises
New Card (Unpublished)Currently Published Content
Front
Back
No published tags.
Pending Suggestions
Field Change Suggestions:
Front
Commit #21167
Empirical risk minimization (ERM)
Back
Commit #21167
Select \(h \in \mathcal H\) so that the empirical error (training error) \(L_{\mathcal S}(h) = \frac 1m \sum_{k=1}^m \ell(h,z_k)\) is minimized.
This can be prone to overfitting depending on the freedom available in \(\mathcal H\).
This can be prone to overfitting depending on the freedom available in \(\mathcal H\).