IS 4422 Deep Learning Architectures 3.0 Credits
Introduces topics that guide how neural networks are designed to meet the representation and prediction needs of different data types, learning tasks, and applications. Presents the development of state-of-the-art architectures and techniques developed for their pre-training and fine-tuning, including for voice transcription, image processing, sequence processing, and graph representation. Covers best practices for building networks with linear, convolutional, recurrent, self-attentive, and preference-tuning components in Python. Students will complete a series of programming assignments and support a team project that develops a deep learning architecture for a relevant data science domain. Students will be prepared to attack new problems using various deep learning methods.
Repeat Status: Not repeatable for credit
Prerequisites: (IS 3330 [Min Grade: D] or CS 3520 [Min Grade: D] or INFO 213 [Min Grade: D] or CS 383 [Min Grade: D]) and (IS 3321 [Min Grade: D] or CS 2110 [Min Grade: D] or MATH 2802 [Min Grade: D] or MATH 3501 [Min Grade: D] or MATH 3701 [Min Grade: D] or INFO 432 [Min Grade: D] or CS 260 [Min Grade: D])