Introduction to Machine Learning: Supervised Learning

This week, we will build our supervised machine learning foundation. Data cleaning and EDA might not seem glamorous, but the process is vital for guiding your real-world data projects. We will explore linear regression as a fundamental statistical technique for solving problems with continuous outcomes.

This week we are building on last week's foundation and working with more complex linear regression models. Students will learn to create linear models with several explanatory and categorical variables, understand 3D data space implications, and interpret coefficients.

This week focuses on shifting from regression to classification tasks using logistic regression. Students will learn about generalized linear models, performance metrics in classification, and practical applications using the sklearn library.

This week covers non-parametric models including k-Nearest Neighbors and Decision Trees. Students will learn about model flexibility, overfitting prevention through pruning, and practical applications with the MNIST dataset and spam classification.

This week focuses on ensemble methods to overcome tree models' tendency to overfit. Students will learn about random forests, bagging, and boosting techniques including AdaBoost and Gradient Boosting.

This week explores Support Vector Machines (SVM), covering essential concepts like hard and soft margins, the kernel trick, and hyperparameter tuning. Students will gain practical experience implementing SVMs and optimizing their performance.