Machine Learning and Security Analysis

Catalog description

Introduction to various machine learning models, providing an overview of many concepts, techniques, and algorithms, as well as demonstrating how these models can be applied to social science research and particularly security studies. This course starts with introducing important machine learning concepts such as classification, regression, overfitting, boosting, clustering, and more. Then the course investigates supervised learning algorithms that are commonly used in academia and industries such as decision trees, random forest, K-nearest neighbor, support vector machines, and neural networks. Next the course focuses on unsupervised learning algorithms, including the K-means clustering algorithm, feature selection and transformation algorithms, and dimensionality-reduction algorithms. In addition, the course provides instructions on the use of Python language and opportunities for students to perform hands-on, self-directed machine learning projects. Finally, information theory and reinforcement learning are briefly discussed. Prerequisite(s): SECR 7601 and SECR 7605 and SECR 7606 Lecture Hours: 3 Lab Hours: 0 Other Hours: 0 Contact Hours: 3 Grade Mode: Normal (A, B, C, D, F) Degree Restrictions: Doctor of Philosophy Schedule Type (Primary): Lecture Schedule Type (Additional): Seminar Small Group Click here for the Schedule of Classes.