Instructor: Prof. Alan Kuntz ([email protected])
Semester: Fall 2025
Course Type: In Person
Schedule: Tu/Th 3:40PM – 5:00PM
Location: WEB L103
Office: MEB 2162
Office Hours: Wed 10:00AM – 10:55AM
This course focuses on modern, practical methods for deep learning with an emphasis on computer vision. Students will implement, train, and debug neural networks and be introduced to ideas underlying state-of-the-art research in computer vision and natural language processing. Topics include learning algorithms, optimization, neural network architectures (including CNNs and elements of RNNs/LSTMs), and techniques for training and fine-tuning networks for tasks such as object recognition, image captioning, NLP, and data management. Python and packages such as NumPy will be used; programming assignments are in Python. Prerequisites include linear algebra, probability and statistics, and multivariate calculus.