Machine Learning . ME 107
This course is meant to introduce students to machine learning and deep learning. ME 107 is taught at the undergraduate level and teaches students how to identify a machine learning problem in the context of real-world applications, mathematically formulate a learning problem, identify when a learning problem is well-posed, under-determined and overdetermined, and develop algorithms and Python code to solve the problem. Students are introduced to the concepts of learning algorithms, overfitting, under-fitting, statistical measures of estimators, optimization approaches to learning, principal component analysis, regression, support vector machines, and artificial neural networks.
Prerequisites: ME 17; or consent of instructor
3
UnitsLetter
Grading1, 2, 3
PasstimeUpper division only
Level LimitEngineering
College
Enrollment Trends
Grading Trends (2)
Rate My Professors (10)
Great professor all-round. Understanding, answers questions with responses tailored to EVERYONE. Posts notes online pretty much day-of, gives gracious extensions and extra credit to patch up your grade, but still expects you to try your best. Dulls the edge of new and difficult material and makes it enjoyable. Archetype of modern lecturers.
he box jumped onto the table. incredible athlete. respecc fosho fosho
Prof Yeung is an incredibly smart professor, sometimes to a fault because I don't think he fully realizes how hard this material (controls theory) is to many students. But he is really caring and accommodating with homework extensions and shorter or simpler homework. Always willing to answer questions and helpful office hours. Hw, midterm, final.
This professor is very research oriented when I asked him about opportunities he is very open to new people in the lab. Just do well I his class and u can get some research in this field easy because of all the practical skills. Hw is super easy
Jeff Moehlis
4.6
Francesco Bullo
4.0
Geoffrey Tsai
5.0
Eric Matthys
1.9