This course follows the Machine Learning I course and builds on the topics originally covered. In this course, students will reconsider the various types of machine learning but now in the context of increasing their efficacy. That is, the focus will be on increasing the efficiency and effectiveness as well as the accuracy of the machine learning methods by evaluating their output and conducting error analyses on their results. Furthermore, the results from the various machine learning methods will be examined, e.g. by ROC, to determine their effectiveness in solving a given problem. Errors will be reported using a variety of methods including misclassification, the Gini Index, and entropy. Students will learn how to adjust a variety of parameters and/or hyperparameters to increase the efficiency of running machine learning methods as well as the accuracy of their output. In addition, underfitting and overfitting will be considered. Regularization and optimization will be introduced. (Prerequisite: DATS331)

View the course schedule to find out details about each course including prerequisites, course objectives, course materials, a snapshot of the syllabi, and session dates.