Machine Learning for Statistical Genomics with Bioconductor
14:00 - 17:00

V. Carey

This lab reviews basic concepts of supervised statistical learning methods, including outcome and feature representation, distance measures, families of learning procedures and their tuning parameters, doubt and outlier decisions, generalization error bounds and estimation. Applications of machine learning procedures to microarray data are presented using the Bioconductor MLInterfaces package. Applications will involve mechanical prediction tasks and substantive interpretation via feature importance measurement.