Machine learning is the science of getting computers to act without being explicitly programmed. In the past decade, machine learning has given us self-driving cars, practical speech recognition, effective web search, and a vastly improved understanding of the human genome. Machine learning is so pervasive today that you probably use it dozens of times a day without knowing it. Many researchers also think it is the best way to make progress towards human-level AI. In this class, you will learn about the most effective machine learning techniques, and gain practice implementing them and getting them to work for yourself. More importantly, you’ll learn about not only the theoretical underpinnings of learning, but also gain the practical know-how needed to quickly and powerfully apply these techniques to new problems. Finally, you’ll learn about some of Silicon Valley’s best practices in innovation as it pertains to machine learning and AI.
Machine learning is the science of getting computers to act without being explicitly programmed. Over the past decade, machine learning has given us self-driving cars, practical speech recognition, effective web search, and it it also giving us a continually improving understanding of the human genome. Machine learning is so pervasive today that most of us use it dozens of times daily without being aware of it. In CS229, students will learn about the latest tools of machine learning, and gain both the mathematical understanding needed to develop their own learning algorithms, as well as the know-how needed to effectively apply learning algorithms to practical problems.
CS294A or CS294W: STAIR (STanford AI Robot) project | Winter 2009
In this class, we’ll spend the entire quarter working on some aspect of the STAIR (Stanford AI Robot) project. The goal of this class is, within one quarter, to help you do a publishable piece of research work in AI.
Artificial Intelligence spans a broad set of tools for building machines that exhibit intelligent behavior. This includes machine learning, probabilistic reasoning (graphical models), planning, search algorithms, CSP, as well as more specialized tools for specific problems such as robotics, computer vision, and natural language processing. In CS221, students will see a broad survey of all of these topics in AI, develop a theoretical understanding of all of these algorithms, as well as implement them yourself on a range of problems. For example, students will implement a learning algorithm to recognize objects (mugs, clocks, stapers, etc.); program a robot arm to move through a nest of obstacles; get a simulated car to execute a fast 180 turn via a controlled skid. More importantly, students will also gain a broad understanding of the mathematical and practical underpinnings of AI, so that after this class, they’ll be able to adapt AI methods to a broad range of their own problems.
CS23N: Robotics and Machine Learning | Spring 2004 (with Geoff Gordon)
This was a freshman seminar which had the goal of introducing students to robotics and machine learning research.