This is the second course of a two-course sequence on machine learning, with a focus on extending to nonlinear modeling with neural networks and higher-dimensional data. Topics include: optimization approaches (constrained optimization, hessians, matrix solutions), deep learning and neural networks, generative models, more advanced methods for assessing generalization (cross-validation, bootstrapping), introduction to non-iid data and missing data. Prerequisites: CMPUT 204 and CMPUT 267; any 300-level Computing Science course; and one of MATH 101, 115, 136, 146, 156. Credit cannot be obtained in both CMPUT 367 and 467.
This is the second course of a two-course sequence on machine learning, with a focus on extending to nonlinear modeling with neural networks and higher-dimensional data. Topics include: optimization approaches (constrained optimization, hessians, matrix solutions), deep learning and neural networks, generative models, more advanced methods for assessing generalization (cross-validation, bootstrapping), introduction to non-iid data and missing data. Prerequisites: CMPUT 204 and CMPUT 267; any 300-level Computing Science course; and one of MATH 101, 115, 136, 146, 156. Credit cannot be obtained in both CMPUT 367 and 467.