CSE 251AMachine Learning: Learning Algorithms
(Formerly CSE 250B.) Algorithms for supervised and unsupervised learning from data. Content may include maximum likelihood; log-linear models, including logistic regression and conditional random fields; nearest neighbor methods; kernel methods; decision trees; ensemble methods; optimization algorithms; topic models; neural networks; and backpropagation. Renumbered from CSE 250B. Students may not receive credit for CSE 251A and CSE 250B. Course may be coscheduled with CSE 151A.
Prerequisites
From the catalog: “graduate standing or consent of instructor. Restricted to students in CS75, CS76, CS78, and CS89. Other graduate students will be allowed as space permits. Recommended preparation: some experience with probability and statistics recommended.”
Courses that list CSE 251A as a prerequisite (1)
- CSE 251B Deep Learning