Classification
Unclassified
Distribution
Distribution A: Approved for public release
Instructor
Dr. Jenny Reed
Duration
Half-day morning course runs 0800-1200
Credits awarded
2 CLPs
Course Fee
Standard Registration*: $300 (includes Government Registrations)
Current Full-Time Students*: $100
* $50 Discount on two courses
Course Description
This short course discusses the fundamental principles of machine learning (ML), which are necessary for executing any machine algorithm successfully. The course begins with an overview of artificial intelligence (AI) and ML, and the different types of problems to which they can be applied. Next, we walk through a simple radar-based machine learning example to demonstrate concepts such as the bias-variance relationship and the curse of dimensionality and how they impact the design of a machine learning model. The course teaches approaches for contending with these concepts, then demonstrates a number of commonly used machine learning algorithms for a variety of different problem types. The course will also have an extended section focusing on the basics of neural networks and deep learning.
Intended Audience
The intended audience of this course include practitioners in science, technology, and engineering disciplines with a technical background, but little experience with machine learning.
Instructor Biography
Dr. Jenny L. Reed is a Principal Research Engineer at the Georgia Tech Research Institute. She received her B.S. degree in Electrical Engineering from Florida Atlantic University in 2006 and her M.S. and Ph.D. degrees in Electrical and Computer Engineering from the Georgia Institute of Technology in 2007 and 2016, respectively. She has over 18 years of experience in radar applications and signal processing. Her research focus is radar signal processing and machine learning (ML) approaches for algorithm development in the areas of electronic protection, automatic target recognition, and airborne, surface, and synthetic aperture radars.