Introduction to Machine Learning
(Same as Electrical and Computer Engineering M146.) Lecture, four hours; discussion, two hours; outside study, six hours. Requisites: course 32 or Program in Computing 10C; Civil and Environmental Engineering 110 or Electrical and Computer Engineering 131A or Mathematics 170A or 170E or Statistics 100A; Mathematics 33A. Introduction to breadth of data science. Foundations for modeling data sources, principles of operation of common tools for data analysis, and application of tools and models to data gathering and analysis. Topics include statistical foundations, regression, classification, kernel methods, clustering, expectation maximization, principal component analysis, decision theory, reinforcement learning and deep learning. Letter grading.
Review Summary
- Clarity
-
8.3 / 10
- Organization
-
10.0 / 10
- Time
-
5-10 hrs/week
- Overall
-
8.3 / 10
Reviews
Overall, I enjoyed taking the class with this professor!
I liked that the professor is always prepared with slides, but often times he would go into great lengths to prove a mathematical concept. I personally didn't like so much proof.
Sriram is decent. The lecture might seem boring, especially with a few "funny" fellow students who constantly raised their hands interrupting him for some "funny" questions of their own (often inconsequential). However, the slides and speeded recordings are enough to learn all the materials.
The class is graded pretty fairly, but in Winter 2024, he changed the format of his final from past exams, likely to how well people were performing. It went from a mostly multiple choice exam to a free response and math heavy final, which was significantly more difficult that the practice exam and the rest of the course. Other than that, the class is fine and since the final is only 20% of the grade it's not that big of a deal.
Displaying all 4 reviews
Course
Grading Information
-
No group projects
-
Attendance not required
-
No midterms
-
Finals week final
-
25% recommend the textbook