Unsupervised Learning Methods is an all-encompassing course aimed at providing students with a comprehensive outline of unsupervised learning methods and their practical applications.

Through a combination of theoretical lectures, hands-on exercises, and real-world projects, students will explore key concepts such as dimensionality reduction, clustering, and recommender systems. The course covers a wide range of topics, including principal component analysis (PCA), multidimensional scaling (MDS), t-distributed stochastic neighbor embedding (t-SNE), K-means clustering, hierarchical clustering, Gaussian mixture models (GMMs), and recommender systems, all of which are implemented using Python and popular machine learning libraries.

By the course’s end, students will have the skills to uncover hidden patterns and structures in unlabelled data, enabling them to extract valuable insights and make informed decisions in various domains.

• Describe unsupervised learning concepts and their
  real-world applications.
• Master dimensionality reduction techniques and their
  respective benefits.
• Explain the principles of principal component analysis
  (PCA) and its practical implementation.
• Execute PCA in Python to achieve dimensionality
  reduction effectively.
• Investigate advanced dimensionality reduction
  methodologies such as multidimensional scaling and
  t-SNE.
• Employ dimensionality reduction techniques on
  image data for comprehensive analysis and
  visualization.
• Design and optimize recommender systems by
  employing both content-based and collaborative
  filtering approaches.
• Explain various clustering methodologies, including
  KNN, GMM, and Hierarchical, and implement them accordingly.