Feature Engineering for Machine Learning

  1. Dimensionality Reduction
    1. Linear Methods
      1. Principal Component Analysis
        1. Variance Explained
          1. Component Interpretation
            1. Scree Plots
              1. Biplot Analysis
              2. Linear Discriminant Analysis
                1. Independent Component Analysis
                  1. Factor Analysis
                    1. Canonical Correlation Analysis
                    2. Non-Linear Methods
                      1. t-SNE
                        1. UMAP
                          1. Isomap
                            1. Locally Linear Embedding
                              1. Multidimensional Scaling
                              2. Neural Network Approaches
                                1. Autoencoders
                                  1. Variational Autoencoders
                                    1. Deep Feature Learning
                                    2. Manifold Learning
                                      1. Manifold Assumption
                                        1. Local vs Global Methods
                                          1. Neighborhood Preservation

                                        Previous

                                        11. Feature Selection Methods

                                        Go to top

                                        Next

                                        13. Advanced Feature Engineering