July 2021
This course explores techniques for machine learning from unlabeled data. You will learn how to find patterns and associations from the data, and use this knowledge to detect anomalies, create recommendation engines, and to improve supervised classification systems. We will then explore how to generate realistic fake data using generative adversarial networks.
-Attendance is mandatory and any student who does not attend at least 90% of the meetings will fail the course automatically. All classes will be online.
-The grade will be based on attendance and class participation (40%) and small practices (60%).
-A missed class can be made up if the student conducts a self-study of the material and presents a summary of it to the instructor.
We will use open-source tools only. Python 3.7.X. will be used with the modules TensorFlow and Keras, among others.
Dr. Juan Carlos Rojas has a master’s and a Ph.D. in electrical engineering from Northeastern University, and a master’s in engineering management from Stanford University. He has led research and development teams for multiple companies in Boston, Silicon Valley, and Costa Rica. Currently, he is an instructor of both electrical engineering and computer science at Texas Tech University-Costa Rica, where he leads the Electrical Exploration Laboratory.