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 introduces unsupervised learning, focusing on dimensionality reduction and clustering. The instructor covers topics such as principal component analysis and the K-means algorithm. Through examples, the lecture explains how unsupervised learning helps find patterns in data without labels, making it ideal for exploratory analysis and data visualization. The concept of PCA is explored, showing how it reduces high-dimensional data to a lower-dimensional space. The lecture also delves into clustering, where data points are grouped based on similarities in their features. The K-means algorithm is discussed as a heuristic approach to clustering, aiming to find representative cluster centers by iteratively assigning data points to the nearest center. The lecture concludes with practical applications of unsupervised learning in recommendation systems, text analysis, and image processing.