Applied Machine Learning

Catalog description

Autonomous and intelligent systems increasingly rely on automated decision making based on statistical models used for classification or prediction. The practical application of machine learning requires understanding the underlying theoretical assumptions behind a wide variety of statistical models, how to analyze the performance of such models, and how to integrate models into data processing pipelines. This course introduces students to supervised and unsupervised machine learning in the context of software engineering, including the analysis of natural language in bug reports and mobile app reviews. Techniques covered include latent Dirichlet allocation, TF/IDF, naive Bayes, linear regression, decision trees, and random forests.