Course Objectives 

1. To introduce the fundamental concepts, workflows, and core trade-offs in machine learning.

2. To deliver an in-depth understanding of regression techniques and tree-based classification algorithms.

3. To introduce advanced ensemble methods for combining weaker machine learning models.

4. To provide comprehensive knowledge of maximum-margin classification using Support Vector Machines.

5. To impart knowledge on various unsupervised learning and clustering approaches.

6. To demonstrate mathematical techniques used to reduce features and handle high-dimensional data.

Course Outcomes 

Students will be able 

1. Formulate machine learning problems and analyze trade-offs like bias-variance and overfitting.

2. Apply and evaluate regression models and decision trees on structured datasets using performance metrics.

3. Design and implement ensemble learning techniques like Bagging, Boosting, and Random Forests to improve accuracy.

4. Analyze and implement Support Vector Machines for linear, non-linear, and multiclass classification tasks.

5. Model and execute graph-based, model-based, and density-based clustering algorithms on unlabeled data.

6. Apply dimensionality reduction techniques like PCA, LDA, and SVD to compress complex feature spaces.