Description

This course will introduce the basic ideas and techniques underlying the design of intelligent computer systems. A specific emphasis will be on the statistical and decision-theoretic modeling paradigm.

By the end of this course, you will have built autonomous agents that efficiently make decisions in fully informed, partially observable and adversarial settings. Your agents will draw inferences in uncertain environments and optimize actions for arbitrary reward structures. Your machine learning algorithms will classify handwritten digits and photographs. The techniques you learn in this course apply to a wide variety of artificial intelligence problems and will serve as the foundation for further study in any application area you choose to pursue.

See the syllabus for slides, deadlines, and the lecture schedule. Readings refer to fourth edition of AIMA unless otherwise specified.

Lecture reference materials

We make lecture recordings available as links to Google Drive, which you can find posted together with other materials on the Syllabus page of this website shortly after the lecture. These links will work only if you are signed into your UC Berkeley Google account.

If you don't have a UC Berkeley account but want to view CS 188 lectures, we recommend the Fall 2018 website instead.

Slides from the Fall 2020 version of the course have been posted for each lecture at the start of semester, as a reference. After lectures, they will be replaced by updated slides. Similarly, notes have been posted from the Fall 2020 version of the course, and will be updated to reflect actual course content.

---