Technique
Regularization
Penalising model complexity (L1, L2, dropout) to reduce overfitting.
Regularization
What should you learn before Regularization?
- Supervised learningLearning from labelled examples to predict a label or value.
- Model evaluation and metricsMeasuring how well a model works: train/test splits, accuracy, precision, recall, F1 and more.
- Bias–variance trade-offThe balance between a model that is too simple and one that is too sensitive to its training data.
- OverfittingA model learning noise in the training data, so it does well in training and badly on new data.
Connections to other concepts
- Helps prevent
- Overfitting
Practise Regularization
- Intermediate Machine Learning Interview Questions2 questions on Regularization
- Advanced Machine Learning Interview Questions2 questions on Regularization