Are you an EPFL student looking for a semester project?
Work with us on data science and visualisation projects, and deploy your project as an app on top of Graph Search.
This lecture delves into logistic regression, continuing from the previous session. It covers the probabilistic interpretation of logistic regression, including multinomial logistic regression. The instructor discusses performance metrics, confusion matrices, and the logistic function's extension to multi-class classification. The lecture also explores K-Nearest Neighbour (KNN) for classification and regression, emphasizing the importance of feature scaling and distance metrics. The session concludes with a detailed explanation of setting hyperparameters, cross-validation, and the curse of dimensionality in KNN. Various practical examples and visualizations are used to illustrate the concepts.