3 Cr. (Hrs.:3 Lec.)
Introduction to the framework of learning from examples, various learning algorithms such as neural networks, and generic learning principles such as inductive bias, Occam's Razor, and data mining. Reviews some statistical learning techniques, but focus is on non-statistical techniques. (2nd)
Course generally offered spring (2nd) semester.
E1. Students should have a thorough understanding of space and time complexity of data structures and algorithms. (CSCI 332)
E2. Students should have a thorough understanding of recursion and recursive problem solving techniques, and list structures and the algorithms associated with them. (CSCI 232)
E3. Students should have a thorough understanding of graphs, trees, and the algorithms associated with them. (CSCI 332)
E4. Students should have a working knowledge of logic and logical methods, including propositional and predicate calculus. (CSCI 246)
R1. Be comfortable with machine learning fundamentals including probability, linear algebra, data analysis, the overall machine learning process and general dimensions of machine learning problems
R2. Have reviewed the statistical techniques of regression, clustering and the nearest neighbor approach.
R3. Understand and be able to implement machine learning algorithms such as neural networks, Bayesian networks and genetic algorithms.
R4. Be able to discuss tradeoffs between different machine learning algorithms, hyperparameter selection heuristics, and bias/variance.
R5. Understand performance metrics and what measures to use to compare results from different models.
R6. Be able to identify and implement ensemble learning techniques.
R7. Be able to develop workable representations for the various approaches, and identify situations in which data manipulation must be used prior to learning.
R8. Understand ethical considerations and assumptions behind the development of a learned model.