Last year there was a streamlined IT assessment included IT 321, 326, 373, 382, 462, 466.
Subhasish and Frank: can you help with 373, 462, and 466? We can review offline.
|
|
|
This course introduces machine learning concepts. Un/semi/supervised, naive baysian, decision trees/regression tree, K-means, K-NN, regression, SVM, neural networks. Prominent models and associated training & operating algorithms, ensemble machine learning: methods and applications, etc, to develop solutions for related problems- classification, regression, anomaly detection, time series prediction, pic-2-pic, sequence to sequence, rule learning, Markov chain learning etc. Related ML concepts for useful preparation of the training datasets for deployed ML models, e.g., utilizing weak supervised learning- incomplete (semi)/inexact/inaccurate supervision.
CSE 5xx (566), Advanced Machine Learning, 3 cr, 3 cl hrs
Prerequisite: CSE 466; or consent of instructor and advisor
Machine learning theory and algorithms. The course will also include additional in-depth advanced topics such as privacy in machine learning, interactive learning, reinforcement learning, autoencoders, online learning, deep learning, Bayesian nonparametric, and additional material on graphical models. Students will be introduced to the most recent advances in the field, both practical and theoretical development.
This course will introduce students to the concepts and tools used in 2D and 3D real-time interactive computer video games. The course will provide students with a theoretical and conceptual understanding of the field of game design, along with practical exposure to the process of creating a game. Topics introduced in this course include graphics, human-computer interaction, artificial intelligence, design iteration, rapid prototyping, game mechanics, dynamics and balance, flow theory, the nature of fun. Additional topics will be selected from parallel processing, networking, and software engineering as needed in game development.