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.

Recordings

We make lecture and Q&A 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. The recordings are also available on Kaltura, which is a service that UC Berkeley partners with that facilitates the cloud recordings of Zoom meetings. All recordings on Kaltura have automatically-generated captions available by default alongside some other useful controls, such as playback speed adjustment.

To access the channel with recordings for this course, please go to this website and create an account if you don’t have one already: https://kaltura.berkeley.edu

Once you have the account, you should be able to access and subscribe to videos in the channel by following this link.

---