Definition, Examples, Importance of Machine Learning

Definition of ML Elements: Algorithm, Model, Predictor Variable, Response Variable, Training - Test Split, Steps in Machine Learning,
ML Models Type: Supervised Learning, Unsupervised Learning and Reinforcement Learning.

Definition of regression, OLS Algorithm, Sum of Squares of residuals, Gradient Descent Algorithm, Cost Function

Evaluation Metrics for Regression Model: MAE, MSE, RMSE, R Square, Adjusted R Square

Comparing MAE, MSE, and RMSE. Significance of Adjusted R square. Overfitting and Underfitting. Bias and Variance.

Regularization methods: Ridge and Lasso Multicollinearity, VIF. Using Python library Sklearn to create the Linear Regression Model and evaluate the model created.

Types of Missing values (MCAR, MAR, MNAR) , Methods to handle missing values

Outliers, Methods to handle outliers: IQR Method, Z Method

Feature Scaling: Definition , Methods: Absolute Maximum Scaling, Min-Max Scaler , Normalization, Standardization, Robust Scaling

Encoding the data: Definition, Methods: OneHot Encoding, Mean Encoding, Label Encoding, Target Guided Ordinal Encoding

Definition. Why is it called the “Regression model”?

Sigmoid Function, Transformation & Graph of Sigmoid Function

Confusion Matrix, Accuracy, Misclassification, TPR, FPR, TNR, Precision, Recall, F1 Score, ROC Curve, and AUC. Using Python library Sklearn to create the Logistic Regression Model and evaluate the model created

Definition, Steps in KNN Model, Types of Distance: Manhattan Distance, Euclidean Distance, ‘Lazy Learner Model’.

Confusion Matrix of Multi Class Classification

Using Python library Sklearn to create the K Nearest Neighbours Model and evaluate the model

Definition, Basic Terminologies, Tree Splitting Constraints, Splitting Algorithms: CART, C4.5, ID3, CHAID

Splitting Methods: GINI, Entropy, Chi-Square, and Reduction in Variance

Using Python library Sklearn to create the Decision Tree Model and evaluate the model created

Ensemble Techniques: Bagging/bootstrapping & Boosting. Definition of Random Forest, OOB Score

K-Fold Cross-Validation

GridSearchCV, Variable Importance. Using Python library Sklearn to create the Random Forest Model and evaluate the model created. Use cases

Definition, Advantages, Baye’s Theorem Applicability, Disadvantages of Naive Baye’s Model, Laplace’s Correction, Types of Classifiers: Gaussian, Multinomial and Bernoulli Using Python library Sklearn to create the Naive Baye’s Model and evaluate the model created

Definition of Clustering, Use cases of Clustering

K Means Clustering Algorithm, Assumptions of K Means Clustering Sum of Squares Curve or Elbow Curve

Dendrogram, Agglomerative Clustering, Divisive Clustering, Comparison of K Means Clustering and Hierarchical Clustering

Using Python library Sklearn to create and evaluate the clustering model

Definition, Curse of Dimensionality, Dimensionality Reduction Technique, When to use PCA, Use Cases

Steps in PCA, EigenValues and EigenVectors, Scree Plot. Using Python library Sklearn to create Principal Components

Model: Definition, Use Cases, Kernel Function, Aim of Support Vectors, Hyperplane, Gamma Value, Regularization Parameter Using Python library Sklearn to create and evaluate the SVM Model