CMPINF 2222 APPLIED DEEP LEARNING

In this course students will learn the foundational assumptions, concepts, and popular tools for applying deep learners to a wide variety of supervised and unsupervised learning problems. The course is hands-on and demonstrates the key concepts and skills through numerous programming examples in lectures, homework assignments, and projects. The course begins by introducing various optimization strategies which underlie how deep learners are trained, before moving to the proper training, validating, and tuning of deep learning methods for supervised learning problems. This portion of the course stresses how the fundamental optimization concepts impact model training. Students will also learn how deep learners relate to and are extensions of generalized linear models in order to reinforce essential supervised learning concepts. The course concludes by focusing on applying deep learning techniques to unsupervised learning problems via variational autoencoders. Multiple autoencoder architecture strategies and training approaches are demonstrated.

Academic Career: Graduate
Course Component: Lecture
Grade Component: Grad LG/SNC Basis
Minimum Credits: 3
Maximum Credits: 3

Current Sections