CSCI 581  Machine Learning  3 Units 

Prerequisite: CSCI 311 with a grade of C or higher; MATH 109 or MATH 120; or Classified Computer Science Graduate Standing.  

Typically Offered: Fall and spring  

This course introduces students to the concepts, theories, and experimental methods of machine learning. This course develops a broad understanding of the issues in implementing machine learning algorithms and systems, especially as they relate to modern data-intensive problems. Topics include but are not limited to experimental design, supervised learning (linear and non-linear regression, parametric and nonparametric learning, support vector machines, Bayesian networks, Hidden Markov Models, and advanced neural networks), unsupervised learning (clustering, dimensionality reduction, and kernel methods), ensemble approaches, learning theory, and reinforcement learning. Students implement and analyze machine learning algorithms. 3 hours discussion.

Grade Basis: Graded  

Repeatability: You may take this course for a maximum of 3 units  

Course Attributes: Upper Division; Laptop required  

Goals: Students will program machine learning solutions to problems in Python and C++ using both bottom-up design from fundamental theory as well as top-down approaches using Python scriptable tools to manage, analyze, and train models with widely available test sets as well as data of their own interest for estimation, prediction, and synthesis. A series of six exercises will be completed for practice leading up to a final project that allows students to pursue the construction and testing of a unique machine learning model of their own design. The course will have a midway assessment of progress as well as quizzes and exercises with a final project instead of a final exam. 

Textbook in Merriam Library:

1. Géron, Aurélien. Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow, 3rd Edition" O'Reilly Media, Inc.", 2022. Available online in Merriam library free to CSU students here.

2. Textbook Jupyter notebook code is available on GitHub for use with Google Colab.

References in Merriam Library:

1. Marsland, Stephen. Machine learning: an algorithmic perspective. Chapman and Hall/CRC, 2nd Edition, 2015 - author site. Available online in Merriam library free to CSU students here.

2. Grus, Joel. Data science from scratch: first principles with python, 2nd Edition. O'Reilly Media, 2019 - book github. Available online in Merriam library free to CSU students here