Lecture
Gaussian Mixture Model: EM final form
Related lectures (49)
Stochastic Simulation: Computation and Estimation
Covers computation and estimation in stochastic simulation, focusing on generating iid replicas and optimal importance sampling.
The Likelihood of Data under a Model
Explores the likelihood of data under a model and the concept of maximum likelihood.
Probabilistic Interpretation: K-Means & GMM
Explores the probabilistic interpretation of K-means clustering and its relation to Gaussian Mixture Models.
Gaussian Mixture Clustering: Expectation-Maximization Algorithms
Explores the Expectation-Maximization algorithm for Gaussian Mixture Clustering and its challenges and practical implementation.
Inference: Exercise 3.2
Covers the topic of likelihood estimation and maximum likelihood estimation in inference.
Model-Based Clustering Methods
Introduces model-based clustering methods using mixture models and latent variables, with practical examples on iris data.
Calcul de V+ (C54-55)
Explains the calculation of V+ in C54-55 with mathematical formulas and examples.
Symbolic Representation of State Spaces
Delves into symbolic representation of state spaces using decision diagrams for high-level Petri nets, showcasing efficient encoding techniques and benchmark results.
End of the M-step derivation
Covers the derivation of the M-step for mu_k and Sigma_k, focusing on key quantities and matrices.
Roulette with Curves and Surfaces
Explores building a roulette, probability distributions on curves, and properties of random surface models, including the groundbreaking Schramm-Loewner evolution processes.