SPEAKER: Dr. Saman Muthukumarana
Director, Data Science Nexus
Associate Professor & Associate Head (Graduate)
Department of Statistics
University of Manitoba
DATE: Thursday, December 12, 2019
TIME: 2:00 pm
PLACE: Engineering & Information Technology Complex (EITC)
Room E1-270 – Borger Room
Fort Garry Campus, University of Manitoba
ORGANIZER: IEEE Robotics, Control, Instrumentation and Measurement Chapter – Winnipeg Section
No registration is required.
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-==-=-=-=-=-=-=-=-==-=-=-=-=-=-
Bayesian methods are powerful for modelling and integrating multiple types and sources of data. These
methods cross into all areas of data analytics as they represent state of belief via a probability distribution.
The key ingredients for a Bayesian analysis are the likelihood function, which reflects information about
the parameters contained in the data, and the prior distribution, which quantifies apriori knowledge about
the parameters before observing data. The prior distribution and likelihood are then combined to form the
posterior distribution, which represents total knowledge about the parameters after the data have been
observed. In complex models, Markov Chain Monte Carlo (MCMC) methods are used learn about the
posterior distribution. In this talk, I will give an overview of use of various Bayesian modelling frameworks
for network models, state space models and Dirichlet process based models with real world applications.
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-==-=-=-=-=-=-=-=-=-=-=-=-=-=-=
Dr. Saman Muthukumarana is an Associate Professor in the Department of Statistics at the University of
Manitoba. (https://www.samanmuthukumarana.com/). He is the Dircetor of Data Science Nexus and
Associate Head (Graduate) in the Department of Statistics. His primary research interests lie broadly in
Bayesian methods and computation for complex models which integrate multidisciplinary applications.
Along with this main theme, he has developed methods to facilitate modelling and inference on non-
standard complex data, which lead to innovative analyses in the areas of social networks, health studies,
sports, customer surveys, user behaviour analysis, and environmental and ecological studies.
=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-==-=-=-=-=-=-=-=-=-=-=-=-=-=-=
Contact: Dr. Nariman Sepehri, PhD, PEng
Chair, IEEE RobConIM, Winnipeg Section
Department of Mechanical Engineering, University of Manitoba
email: Nariman.sepehri@umanitoba.ca, phone: (204)4749821
