Sumários
Worked exercises
31 maio 2024, 13:00 • João Pedro Castilho Pereira Santos Gomes
Problem set on clustering: Q1, Q2, Q4, Q6, Q7, Q10.
Clustering based on Gaussian mixture models
28 maio 2024, 10:00 • João Pedro Castilho Pereira Santos Gomes
The expectation-maximization (EM) algorithm for statistical inference. The EM algorithm for GMMs. Relation with Lloyd's algorithm for k-means. Model complexity and data requirements. Model order selection: Akaike and Bayesian information criteria. Density estimation. [Murphy 11.4-11.4.2.5, 11.4.2.7, 11.5]
Worked exercises
27 maio 2024, 11:30 • João Pedro Castilho Pereira Santos Gomes
Problem set on clustering: Q1, Q2, Q3, Q4, Q6, Q7, Q10.
Spectral clustering; Gaussian mixture models
21 maio 2024, 10:00 • João Pedro Castilho Pereira Santos Gomes
Properties of the eigenvalues and eigenvectors of the Laplacian. The Fiedler eigenvalue/eigenvector. Graph cuts and graph partitioning. Ratio and normalized cuts and their relaxation. Spectral clustering algorithm. Gaussian mixture models (GMM). Maximum-likelihood formulation and the minorization-maximization (MM) approach for iterative optimization [Zaki 16.1, 16.2-16.2.2, Murphy 11.2-11.2.1, 25.4]