[Forum SIS] short course bayesian Networks

[Dip. Scienze Statistiche - Mi]

The Department of Statistical Sciences, Università Cattolica del Sacro Cuore,  has organized a short course



Understanding Bayesian Networks

with Examples in R



Instructor

Marco Scutari

University of Oxford

 January, 23 - 24 - 25, 2017

Aula G. 052



Università Cattolica del Sacro Cuore - Milano

Largo Gemelli,1 - Edificio Lanzone 18

The purpose of this short course is to introduce the fundamental ideas underlying Bayesian networks; to cover their uses in data analysis; and to demonstrate the use of related R packages using real data. The course will cover all three aspects of Bayesian networks: structure learning, parameter learning and inference. Advanced topics such as causal inference, handling missing data and model averaging will build on this material. Finally, some analyses from the literature will be
replicated in R to provide examples on how to apply Bayesian networks to real-world data.

LECTURE 1: DEFINITIONS
(Jan 23, 10-13)

·         Relevant concepts graph theory: graphs, DAGs, cycles.

·         Graphical separation and probabilistic independence.

·        Markov property and factorisation into local distributions.

·        The definition of Bayesian networks.

·        Markov blankets.

·        Parametric assumptions: discrete, Gaussian and conditional linear Gaussian Bayesian networks.
LECTURE 2: FUNDAMENTALS OF INFERENCE
(Jan 23, 14.30-17.30)

·        Exact and approximate inference.

·        Junction trees.

·        Logic Sampling and Likelihood Weighting.

·        Diagnostic and prognostic models.

·        Naive Bayes and Tree-Augmented Naive Bayes classifiers.
LECTURE 3: ADVANCED INFERENCE
(Jan 24, 10-13)

·        Causal inference

·        Missing data: Expectation Maximisation and Data Augmentation

·       Predictions, from a single model and from an ensemble.
LECTURE 4: FUNDAMENTALS OF STRUCTURE LEARNING
(Jan 24, 14.30-17.30)

·        Structure learning.

·        Constraint-based, score-based, hybrid algorithms.

·        Common tests and scores.
LECTURE 5: ADVANCED STRUCTURE LEARNING, PARAMETER LEARNING
(Jan 25, 10-13)

·        Graph priors (on the space of DAGs) in structure learning.

·        Parameter learning.

·        Model averaging.
LECTURE 6: HANDS-ON EXAMPLES
(Jan 25, 14.30-17.30)

·        Protein signalling analysis from Sachs et al. (Sachs et al., Science, 2005).

·        Genomic association and prediction from Scutari et al. (Scutari et al., Genetics, 2014).

·        Modelling attitudes to business creation at universities (Garcia, Puga and Scutari, 2014, International Technology, Education and Development Conference)





Attendance is free. However for organizational reasons, please register by sending an email to

dip.scienzestatistiche at unicatt.it<mailto:dip.scienzestatistiche at unicatt.it>


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.stat.unipg.it/pipermail/sis/attachments/20161206/3dcd318c/attachment-0001.html>