INS Workshop on Bayesian Data Analysis
With Michael Betancourt, taking place between May 17th to 19th, 2022
Salle informatique 204 - b timent p dagogique (Facult de M decine,
27, Boulevard Jean Moulin - 13005 Marseille, France)
Due to the importance and common use of Bayesian framework for inference and prediction, the
advanced techniques in probabilistic programming languages to overcome the inference
difficulties with big data complemented with big models have been receiving increasing attention
in this context. Stan is a popular platform for facilitating inference, providing an expressive
modeling language and implementing state-of-the-art algorithms to draw subsequent Bayesian
inferences.
We are very happy to announce the INS courses on "Bayesian Data Analysis", with Michael
Betancourt, a core developer of Stan and expert in Hamilton Monte Carlo. The courses begin by
surveying Bayesian inference, Bayesian computation and a principled introduction to Stan.
With a solid foundation, we will move onto to the elements of a robust Bayesian workflow in
practice and then continue to the problem of interest to neuroscienist such as source localization
in Neuroimaging.
The courses are highly interactive, with exercises demonstrating a principled Bayesian workflow
and range of modeling techniques run in Python environment. Courses run for 3 days and
include material spanning Probabilistic modelling, identifiability and degeneracy, Bayesian
workflows and Hierarchical modelling.
Prerequisites for the course
The course will assume familiarity with the basics of calculus, linear algebra, and probability
theory. For a self-contained introduction to the latter please review my probability theory,
conditional probability theory, and common probability densities case studies. The last will be
particularly relevant.
UMR 1106 – Institut de Neurosciences des Syst mes INS
Facult des Sciences M dicales et Param dicales Campus Timone
27 Boulevard Jean Moulin - 13385 Marseille cedex 05 – France
Tel : + 33 (0) 4 91 32 42 51 - Fax : + 33 (0) 4 91 78 99
AGENDA
Day 1, May 17th
9:30-12:30
COFFEE BREAK 11:00-11:30
Lecture on probabilistic modelling
- Modelling and inference
- Generative Modeling
13:30-17:00
Exercises on modelling, Poisson model of spike counting
Day 2, May 18th
9:30-12:30
COFFEE BREAK 11:00-11:30
Identifiability and degeneracy lecture
- Robust workflows for Bayesian modelling
- Identifiability and degeneracy
End of morning: examples and discussion
13:30-17:00
Model building Bayesian workflow lecture
- Bayesian model building workflow
- Hands on modelling: MEG/sEEG source analysis
15:00-17:00
Exercises and discussion
The nominal material is based around the Poisson progression
in https://betanalpha.github.io/assets/case_studies/principled_bayesian_workflow.html,
Day 3, May 19th
9:30-12:30
COFFEE BREAK 11:00-11:30
Hierarchical modeling lecture and exercises from the first 2 days.
End of morning: examples and discussion
13:30-17:00
Exercises on modelling: temporal models with ODEs
Open discussion with participant models, datasets and questions
UMR 1106 – Institut de Neurosciences des Syst mes INS
Facult des Sciences M dicales et Param dicales Campus Timone
27 Boulevard Jean Moulin - 13385 Marseille cedex 05 – France
Tel : + 33 (0) 4 91 32 42 51 - Fax : + 33 (0) 4 91 78 99
Please, note that the training is taking place in the building right next to the entrance of the
Campus Timone (b timent p dagogique, yellow/green building) and NOT at the seat of the
INS.
To learn more about the event and to register , please see here:
https://hub.thevirtualbrain.org/news/index.html
and here