BME I9400 Special Topics in Machine Learning
This course provides a broad overview of machine learning and pattern recognition, with an emphasis on techniques that are commonly used in practice to make inferences from biomedical data sets. The course begins with a review of probability theory and random variables. 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.
Prerequisite
Undergraduate course in probability and statistics. Basic understanding of linear algebra.
Contact Hours
2.5hr./wk.