Machine Learning

Lecture, three hours; discussion, one hour. Requisites: courses 115A, 164, 170A or 170E or Statistics 100A, and Computer Science 31 or Program in Computing 10A. Strongly recommended requisite: Program in Computing 16A or Statistics 21. Introductory course on mathematical models for pattern recognition and machine learning. Topics include parametric and nonparametric probability distributions, curse of dimensionality, correlation analysis and dimensionality reduction, and concepts of decision theory. Advanced machine learning and pattern recognition problems, including data classification and clustering, regression, kernel methods, artificial neural networks, hidden Markov models, and Markov random fields. Projects in MATLAB to be part of final project presented in class. P/NP or letter grading.

Review Summary

Clarity
6.7 / 10
Organization
6.7 / 10
Time
10-15 hrs/week
Overall
5.0 / 10

Reviews

    Quarter Taken: Fall 2023 In-Person
    Grade: N/A

    This class deviated greatly from what I heard Math 156 was in the past—a heavy emphasis on mathematical proofs of concepts in classical machine learning such as convergence conditions and upper/lower bound finding; in contrast, we took a conceptual whirlwind tour of classical and deep learning models/techniques which was kind of disorganized, and nobody knew how to prepare for the midterms which were not by themselves difficult, but were rather made difficult by the uncertainty surrounding what would be tested and how. The group project is completely open-ended and can be as interesting as you'd like it to be, which I did find to be pretty cool. Overall the class is a decent intro to machine learning although I would recommend building a solid foundation elsewhere if possible.

Course

Instructor
Krishnagopal, S.
Previously taught
23F 23W

Grading Information

  • Has a group project

  • Attendance not required

  • 2 midterms

  • No final

  • 100% recommend the textbook

Previous Grades

Grade distributions not available.