Special Topics in Machine Learning

Catalog description

This course provides a broad overview of machine learning and pattern recognition, with an emphasis of techniques that are commonly used in practice to classify biomedical data sets. The course begins with a review of probability theory and random variables, which are the foundation for statistical learning. We will then survey a variety of supervised and unsupervised architectures, beginning with linear and logistic regression and ending up at modern-day techniques such as convolutional neural networks. Throughout the course, students acquire hands-on experience with the presented concepts via application to real-world data sets from a variety of domains. The course assumes a basic knowledge of linear algebra and probability theory.