CSCI5521: Machine Learning Fundamentals

3 Credits

Problem formulations and concepts of generalization, overfitting/under-fitting and model selection. Statistical foundations: maximum likelihood, maximum a posteriori, Expectation Maximization (EM), Bayesian estimation, and non parametric methods. Mathematical foundations and optimization: gradient descent, back propagation, regularization, quadratic programming. Perceptrons, neural networks and deep learning methods. Kernel methods and Support Vector Machines (SVMs). Machine Learning ethics. prereq: STAT 3021, (CSci 2033 or Math 2142 or Math 4242)

View on University Catalog

All Instructors

A- Average (3.575)Most Common: A (49%)

This total also includes data from semesters with unknown instructors.

3051 students
SNWFDCBA
  • 4.93

    /6

    Recommend
  • 4.91

    /6

    Effort
  • 5.18

    /6

    Understanding
  • 4.99

    /6

    Interesting
  • 5.10

    /6

    Activities


      Contribute on our Github

      Gopher Grades is maintained by Social Coding with data from Summer 2017 to Spring 2025 provided by the University in response to a public records request

      Not affiliated with the University of Minnesota

      Privacy Policy