CS 444

Credit: 3 OR 4 hours.

Provides an elementary hands-on introduction to neural networks and deep learning with an emphasis on computer vision applications. Topics include: linear classifiers; multi-layer neural networks; back-propagation and stochastic gradient descent; convolutional neural networks and their applications to object detection and dense image labeling; recurrent neural networks and state-of-the-art sequence models like transformers; generative adversarial networks and variational autoencoders for image generation; and deep reinforcement learning. Coursework will consist of programming assignments in a common deep learning framework. Those registered for 4 credit hours will have to complete a project.

3 undergraduate hours. 4 graduate hours. Prerequisite: Multi-variable calculus, linear algebra (MATH 225 or MATH 257 or MATH 415 or MATH 416 or ASRM 406), data structures (CS 225 or equivalent), CS 361 or STAT 400. No previous exposure to machine learning is required.