LAST UPDATE: FEBRUARY 9, 2018
In this introductory course, students will learn important basic concepts in machine learning with a series
of hands-on training exercises using R and RStudio. We will explore and discuss different machine learning
training strategies and learn on the most important algorithms used in this field such as Random Forests
and Support Vector Machines. The capabilities of R caret package will be extensively used and applications
in genetics and genomics will be performed with data from public databases. At the end of the course, students
will be able to implement a machine learning strategy and to critically evaluate an algorithm’s performance
in classification and regression problems. For a detailed course outline, click
TARGET AUDIENCE: Graduate students, clinical scholars, bioinformaticians, biologists and health science researchers with a strong interest in statistical methods
PREREQUISITES: Introductory to intermediate programming proficiency in R and R Studio; Basic foundation in statistical modelling (e.g. linear regression).
Dr. Joel Correa da Rosa holds a M.Sc. degree in Probability and Statistical Inference from State University of Campinas (Sao Paulo / Brazil) and a PhD in Decision Support Methods from the Pontifical Catholic University (PUC-Rio- Rio de Janeiro/Brasil). He worked as an Associate Professor at Federal University of Paraná and Federal Fluminense University. From 2012 to 2015, Dr. Correa da Rosa worked as a Research Associate in Center of Clinical and Translational Science and Laboratory of Investigative Dermatology at the Rockefeller University, becoming Director of Biostatistics in 2015. In 2017 he joined the Population Health Science & Policy Department at the Icahn School of Medicine at Mount Sinai. His expertise includes data analysis, statistical programming, multivariate analysis, and machine learning methods for classification, regression and clustering. He is proficient in R programming and very familiar with SAS, S-Plus, SPSS and MATLAB.