CSE 151 - Introduction to Artificial Intelligence: Statistical Approaches



An introduction to theoretical issues and computational techniques arising from a comparison of human and machine intelligences. Knowledge representation languages; problem-solving heuristics; machine learning and application areas including vision, robotics, and natural language understanding will be reviewed.

Course Objectives: 

This course surveys central issues and techniques of AI. Programming assignments and selected readings will acquaint the general CSE student with AI methods, as well as preparing those with special interests in AI for further study in the area.

The goal of this class is to provide a broad introduction to machine-learning. The topics covered in this class include some topics in supervised learning, such as k-nearest neighbor classifiers, decision trees, boosting and perceptrons, and topics in unsupervised learning, such as k-means, PCA and Gaussian mixture models. We will also look at some basics of learning theory. The topics covered in this class will be different from those covered in CSE 150.

Recommended preparation: Students are expected to have some familiarity with linear algebra and probability, and should be able to program in some language. Taking CSE 150 is not a prerequisite, but a big plus! 

Laboratory Work: 

Programming assignments on Unix work stations using Lisp and Prolog.


CSE 100 or Math 176.  Please see Prerequisites Page


One quarter per year, generally in Spring.