Probabilistic modelling and inference made easy
Department of Statistics, Columbia University
Tuesday 28th April
5:45pm – Light refreshments in the foyer of the Chemical and Biomolecular Engineering Theatre, The University of Melbourne.
6:15pm – Seminar in Chemical and Biomolecular Engineering Theatre, The University of Melbourne.
7:30pm – Dinner with Bob at Café Italia, University St, Carlton.
Dr Bob Carpenter is a research scientist in computational statistics (Columbia University). He designed the Stan probabilistic programming language and is one of the Stan core developers.
Bob has a Ph.D. in cognitive and computer science (University of Edinburgh), worked as a professor of computational linguistics (Carnegie Mellon University), and as an industrial researcher and programmer in speech recognition and natural language processing (Bell Labs, SpeechWorks, LingPipe).
Good software tools are essential for effective data analysis. In this talk, Bob will introduce Stan, a probabilistic programming language for expressing statistical models. It implements Bayesian inference (via MCMC sampling) and penalised maximum likelihood estimation (via optimisation). Stan is similar to BUGS, but more general, scalable and efficient. It is provided as open-source software, with interfaces to other widely used languages (including R, Python and MATLAB). Over 100 papers have already been published using Stan across the biological, physical and social sciences.
Bob will present a brief overview of Stan and how it works, followed by a few case studies and examples of problems for which Stan is ideally suited.
More information on Stan is available at: http://mc-stan.org/
You are invited to join Bob for dinner at Café Italia after the meeting.
|Time:||6:15 pm - 7:30 pm|
|Location:||Chemical and Biomolecular Engineering Theatre,
Monash Road (Building 165),
University of Melbourne,