ECE 5230 - Engineering Applications in Deep Learning

Credits: (3)
Typically Taught Spring Semester: Full Sem
Description: This course covers deep learning architectures with a focus on learning end-to-end models for these tasks, particularly image and signal processing. Students will learn to implement, train and debug their own deep neural networks and gain a detailed understanding of cutting-edge research in this field. Strong emphasis will be placed on real-world applications for both solving engineering problems using these methods as well as practical techniques for training and fine-tuning the networks. Case studies will be drawn from medical imaging, semiconductors, and audio signal processing.
Pre-requisite(s): ECE 1400, ECE 3210, MATH 3410, and either MATH 2250 or MATH 2270.