About

Statistics 652: Statistical Learning (2 units)

Course Description:

Statistical machine learning overview. Choosing a learning algorithm. Supervised learning including classification and prediction methods, nearest neighbors, naive Bayes, decision trees and rules, random forests, neural networks, linear regression and logistic regression. Unsupervised learning including clustering and principle components. Model performance and evaluation. Confusion matrix. Report writing.

Prerequisites:

Post-baccalaureate standing.

Possible Instructional Methods:

Entirely On-ground, or Entirely Online, or Hybrid.

Grading:

A-F or CR/NC (student choice).

Student Learning Outcomes

Upon successful completion of this course students will be able to:

  1. Use software to learn from data.
  2. Critically evaluate learning models.
  3. Extract data from large data source to learn from data.
  4. Create reproducible reports.