Data Mining - Spring 2023

Explore fundamental data mining concepts and algorithms through this comprehensive university course covering statistical principles, similarity measures, clustering techniques, and dimensionality reduction methods. Master k-grams and Jaccard similarity for text analysis, then delve into min hashing techniques for efficient similarity estimation. Learn various distance metrics and embedding representations before progressing to clustering algorithms including hierarchical clustering, k-means, and spectral clustering. Discover streaming algorithms like Misra-Gries and sketch algorithms including count sketch for handling large-scale data. Study regression techniques from linear to nonlinear models with regularization, followed by dimensionality reduction methods such as PCA, SVD, random projection, and frequent directions. Examine multidimensional scaling (MDS) and linear discriminant analysis (LDA) for data visualization and classification. Investigate distance metric learning and outlier detection techniques, then explore matrix completion problems and the PageRank algorithm for web search and network analysis. Conclude with MapReduce framework for distributed computing and a comprehensive review of all covered topics.