Machine learningMachine learning

Regularizirana logistička regresija

Regularizirana logistička regresija proširuje standardnu logističku regresiju dodavanjem L1 (lasso), L2 (ridge) ili elastic net penalizacije log-vjerojatnosti, čime se koeficijenti smanjuju prema nuli i sprječava prekomjerno prilagođavanje (overfitting). To je zadani izbor za binarnu ili multinomijalnu klasifikaciju kada su potrebne interpretibilne, rijetke ili stabilne procjene koeficijenata u visokodimenzionalnim ili kolinearnim prostorima značajki.

Otvorite u MethodMindUskoroVideoUskoroDownload slides

Pročitajte cijelu metodu

Samo za članove

Prijavite se besplatnim računom kako biste pročitali ovaj odjeljak.

Prijavite se

Method map

The neighbourhood of related methods — select a node to explore.

+4 more

Izvori

  1. Tibshirani, R. (1996). Regression shrinkage and selection via the lasso. Journal of the Royal Statistical Society: Series B, 58(1), 267–288. DOI: 10.1111/j.2517-6161.1996.tb02080.x
  2. Hastie, T., Tibshirani, R., & Friedman, J. (2009). The Elements of Statistical Learning (2nd ed., Ch. 4, 18). Springer. ISBN: 978-0-387-84857-0

Kako citirati ovu stranicu

ScholarGate. (2026, June 3). Regularized Logistic Regression (L1 / L2 / Elastic Net Penalized Binary and Multinomial Classification). ScholarGate. https://scholargate.app/hr/machine-learning/regularized-logistic-regression

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Citirana u

ScholarGateRegularized Logistic Regression (Regularized Logistic Regression (L1 / L2 / Elastic Net Penalized Binary and Multinomial Classification)). Preuzeto 2026-06-15 s https://scholargate.app/hr/machine-learning/regularized-logistic-regression · Skup podataka: https://doi.org/10.5281/zenodo.20539026