Skip to Content
Home /  Courses And Programs / Introduction to Machine Learning

Introduction to Machine Learning

A broad introduction to principles, algorithms, and foundations of machine learning. The main topics include linear and nonlinear models, for supervised and unsupervised learning, such as regression models, naïve Bayes, decision trees, gradient boosting, matrix factorization, clustering, perceptrons, support vector machines, and neural networks. The main principles will be related to predictive analytic framework, such as generative vs discriminative decisions, errors estimations and evaluation measures, model complexity and bias/variance, dimensional reduction, regularization methods, ensemble and boosting methods. The main foundations will apply mathematical concepts in calculus, linear algebra, optimization, probability and statistics.

Course Topics:

  • Linear Regression, parameter estimation, predictions and models, non-linear regression, matrix and vector projections
  • Logistic Regression, maximum likelihood, classification
  • Penalty regression, LASSO, Ridge, regularization
  • Generative models, Naïve Bayes, Linear/Quadratic discrimination, Bayes rule and conditional probabilities
  • Divide and conquer, decision trees, random forests, bagging, gradient boosting, nearest neighbors
  • Representational/factor models, PCA,SVD, matrix factorization
  • Perceptron, support vector machine, constrained optimization, kernels
  • Neural networks, Convolution neural networks

Learning Outcomes

By the end of the course students will be able to:

  • Demonstrate a fundamental understanding of machine learning and its foundations
  • Describe the mathematical principles and features of machine learning models and algorithms
  • Recognize and recall mathematical operations that are used in machine learning models and algorithms
  • Demonstrate ability to implement basic versions of model algorithms and evaluate model performance
  • Describe tradeoffs between different models and the basis for those tradeoffs
  • Describe applications and situations that are appropriate for different models and the basis for those choices

Course typically offered: In-class during the Spring '20 academic quarter

Prerequisites: This course is aimed very broadly at undergraduates in mathematics, science, and engineering. Students are expected to be comfortable with calculus and have some familiarity with linear algebra, probability, and should be able to program in some language (preferably Python).

Next steps: Upon completion, consider coursework in our specialized certificate in Machine Learning Methods to continue learning.

More Information: For more information about this course, please contact

Course Number: CSE-41327
Credit: 4.00 unit(s)