Machine Learning with Scikit-Learn

  1. Improving Model Performance
    1. Hyperparameter Tuning
      1. Understanding Hyperparameters
        1. Manual Tuning
          1. Grid Search
            1. GridSearchCV
              1. Parameter Grids
                1. Cross-Validation Integration
                  1. Computational Considerations
                  2. Randomized Search
                    1. RandomizedSearchCV
                      1. Parameter Distributions
                        1. Efficiency Benefits
                        2. Bayesian Optimization
                          1. Hyperparameter Tuning Best Practices
                          2. Model Diagnostics
                            1. Learning Curves
                              1. Training vs Validation Performance
                                1. Sample Size Effects
                                  1. Bias-Variance Analysis
                                  2. Validation Curves
                                    1. Parameter vs Performance
                                      1. Optimal Parameter Selection
                                      2. Residual Analysis
                                        1. Error Patterns
                                          1. Assumption Validation
                                          2. Feature Importance Analysis
                                            1. Model-specific Importance
                                              1. Permutation Importance
                                            2. Addressing Overfitting
                                              1. Regularization Techniques
                                                1. Early Stopping
                                                  1. Dropout
                                                    1. Data Augmentation
                                                      1. Cross-Validation
                                                      2. Addressing Underfitting
                                                        1. Model Complexity Increase
                                                          1. Feature Engineering
                                                            1. Reducing Regularization
                                                            2. Imbalanced Dataset Handling
                                                              1. Class Distribution Analysis
                                                                1. Resampling Techniques
                                                                  1. Random Oversampling
                                                                    1. Random Undersampling
                                                                      1. SMOTE
                                                                      2. Cost-sensitive Learning
                                                                        1. Threshold Adjustment
                                                                          1. Ensemble Methods for Imbalanced Data

                                                                        Previous

                                                                        7. Model Evaluation and Metrics

                                                                        Go to top

                                                                        Next

                                                                        9. Unsupervised Learning