{"id":44,"date":"2019-07-28T16:16:16","date_gmt":"2019-07-28T16:16:16","guid":{"rendered":"https:\/\/scholarblogs.emory.edu\/smi2020\/?page_id=44"},"modified":"2021-07-13T17:13:04","modified_gmt":"2021-07-13T17:13:04","slug":"program","status":"publish","type":"page","link":"https:\/\/scholarblogs.emory.edu\/smi2021\/program\/","title":{"rendered":"Conference Schedule and Full Program"},"content":{"rendered":"\n

The conference program and session recordings can be accessed via the online program website<\/a>.<\/u><\/p>\n

Program at a Glance<\/h2>\n\n\n

 <\/h3>\n

Founders Talk<\/h4>\n

\"\"<\/p>\n

Timothy Johnson<\/a> (Professor, Department of Biostatistics, University of Michigan)<\/p>\n

Talk Title: A Bayesian semi-parametric model for functional near-infrared spectroscopy data<\/p>\n

 <\/div>\n
\n
<\/div>\n

Keynote Speakers<\/span><\/h4>\n

\"\"<\/p>\n

Tom Nichols<\/a> (Professor of Neuroimaging Statistics, Nuffield Department of Population Health, University of Oxford)<\/p>\n

Talk Title: Neuroimaging Statistics for Population Scale Data<\/p>\n

\"\"<\/p>\n

Vince Calhoun<\/a> (Director, Tri-institutional Center for Translational Research in Neuroimaging and Data Science)<\/p>\n

Talk Title: Swimming in a sea of under-explored dynamics: A survey of approaches for capturing time-varying connectivity<\/p>\n

\n

Short Course<\/span><\/h2>\n

Introduction to Deep Learning <\/span><\/h4>\n

Deep Learning is ubiquitous today across data-driven applications as diverse as machine vision, natural language processing, and super-human game-playing. This half-day workshop will introduce the fundamentals of the main types of deep learning models.  You will also learn the motivation and use cases of deep learning through hands-on exercises using R and Python in the cloud environment. This workshop is designed for the audience with a statistics background. No software download or installation is needed, everything is done through an internet browser (Chrome or Firefox) in Databricks free cloud environment.<\/p>\n

Topics:<\/p>\n