Introduction to Machine Learning CMSC-678
The course will provide extensive grounding in machine learning models and its utility to make predictions. The course will go over the mathematical foundations and real world applications of machine learning. The course will slowly move over the topics like prediction and classification problems, kernel methods, generative modeling, probability theory, optimization theory, representation learning, neural networks, and many more. In process, the course would teach some of the limitations of machine learning and how to augment them with better methods.
Slides, materials, and project information for this iteration of machine learning course are borrowed from Andrew Ng, John Guttag, Sanjoy Dasgupta, Tom Mitchell, Frank Ferraro, Hal Daume III, Trevor Hastie, Robert Tsibrani, Roger Grosse.
Why Visit this Website:
- Links to the Coding Assignments will be provided on this website.
- Links to the Readings for Presentations will be provided on this website. These readings are optional to choose, if you select a paper from a list of top-tier CS conferences or journals.
- There might be one or two invited talks on Machine Learning from industry practitioners. Information will be provided on this webpage
Discussion Forum
This class will use the CMSC-678 Discussion forum in the following SLACK-LINK. The forum will be a platform for questions from assignments, annoucements, and discussion on specific topics taughts in the class. For any sensitive issue, please email me: manas@umbc.edu .