Graduate Education at APG

Summer 2026:

Modern Machine Learning (ELEG 845)

Course Description: Machine learning can be applied to numerous engineering problems. In this course, we will cover data preprocessing, dimensionality reduction methods, regression techniques such as linear, multilinear, ridge, lasso and logistic regression, classification methods such as K-nearest neighbor, decision trees, support vector machines, naive Bayesian and random forest and unsupervised clustering algorithms. Training neural networks with back propagation and reinforced learning methods, convolution and recurrent neural networks and deep learning networks will be introduced. MATLAB(R) will be used to illustrate the various methods.

Prerequisites: Students are expected to have an undergraduate background in signals and systems theory or permission from the instructor.

Textbook: “The Elements of Statistical Learning, Data Mining, Inference and Prediction” by Hastie, Tibshirani and Friedman, Springer, 2nd Edition.

Method of Instruction: Delivery is through live lectures; however, lecture notes will be posted each week on-line to accommodate students with busy travel schedules. Grades will be based from homework assignments and two exam grades.