Dieses Dokuwiki verwendet ein von Anymorphic Webdesign erstelltes Thema.


This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
lectures [2020/07/20 16:18]
etore [Computational biology]
lectures [2020/07/20 16:23] (current)
etore [Fundamentals of probabilistic data mining]
Line 226: Line 226:
 3 ECTS, C. 13.5h, L. 4.5h, Xavier Alameda-Pineda 3 ECTS, C. 13.5h, L. 4.5h, Xavier Alameda-Pineda
-This lecture introduces fundamental concepts and associated numerical methods in model-based clustering, classification and models with latent structureThese approaches are particularly relevant to model random vectors, sequences or graphsto account for data heterogeneity, and to present general principles in statistical modelling. The following topics are addressed: +**Content:** This courses introduces probabilistic models with latent variables, and the associated algorithms to estimate the parameters and perform inference over the latent variablesSuch models are used for unsupervised tasks such as clustering and source modelingas well as for supervised tasks such as classification and regressionYou will discover the basic probabilistic models as well as more advanced techniques. 
-   * Principles of probabilistic data mining and generative models; models with latent variables + 
-   Probabilistic graphical models +The following topics are addressed: 
-   * Mixture models and clustering +   * Principles of probabilistic data mining and generative models 
-   PCA and probabilistic PCA +   Latent variables and probabilistic graphical models 
-   Generative models for series and graphs : hidden Markov models+   * Mixture models 
 +   The linear-Gaussian model and probabilistic PCA 
 +   Markov models for time series with continuous and discrete latent variables 
 +   * Variational inference and variational auto-encoders 
 +At the end of the course, the student will have basic knowledge in the most common probabilistic models with latent variables. Therefore, the student will be able to perform model-based clustering, analysis and segmentation of time-series with hidden Markov models, build a graphical model associated with a given distribution, represent numerical multivariate data with missing coordinates into planes and work with state-of-the-art non- linear regression models based on variational autoencoders. 
 +**Prerequisite:** Fundamental principles in probability theory (conditioning) and statistics (maximum likelihood estimator and its usual asymptotic properties). 
 +**Evaluation:** The first session combines a written exam (E1) and the reports of the three practical sessions (P). The final mark of the first session is obtained as (E1+P)/2. The second session consists of only a written exam (E2) which constitutes the final grade.  
 [[http://formations.univ-grenoble-alpes.fr/fr/catalogue/master-XB/sciences-technologies-sante-STS/master-mathematiques-et-applications-program-master-mathematiques-et-applications/parcours-master-of-science-in-industrial-and-applied-mathematics-msiam-subprogram-parcours-master-of-science-in-industrial-and-applied-mathematics-msiam/ue-fundamentals-of-probalistic-data-mining-ISVJOLHU.html|Detailed description of GBX9MO17]] ; [[lectures|MSIAM Course list]] ; [[m2courses|Semester 3 (MSIAM tracks)]] [[http://formations.univ-grenoble-alpes.fr/fr/catalogue/master-XB/sciences-technologies-sante-STS/master-mathematiques-et-applications-program-master-mathematiques-et-applications/parcours-master-of-science-in-industrial-and-applied-mathematics-msiam-subprogram-parcours-master-of-science-in-industrial-and-applied-mathematics-msiam/ue-fundamentals-of-probalistic-data-mining-ISVJOLHU.html|Detailed description of GBX9MO17]] ; [[lectures|MSIAM Course list]] ; [[m2courses|Semester 3 (MSIAM tracks)]]
lectures.txt · Last modified: 2020/07/20 16:23 by etore
Dieses Dokuwiki verwendet ein von Anymorphic Webdesign erstelltes Thema.
www.chimeric.de Valid CSS Driven by DokuWiki do yourself a favour and use a real browser - get firefox!! Recent changes RSS feed Valid XHTML 1.0