Machine Learning
146 views
Regularization
Quick Definition
Techniques constraining model complexity to prevent overfitting
Full Definition
Techniques that constrain or penalize model complexity to prevent overfitting and improve generalization.
Examples
L1/L2 regularization, dropout, early stopping
Related Terms
overfitting
lasso
ridge-regression
More Machine Learning Terms
Gaussian Mixture Model
Probabilistic model using multiple Gaussian distributions
Lasso Regression
Regularized regression using L1 penalty for feature selection
Random Forest
Ensemble of decision trees that votes on predictions
Unsupervised Learning
Discovering hidden patterns in unlabeled data
Feature Engineering
Creating and transforming input variables to improve performance
Active Learning
Algorithm selecting most informative data points for labeling