Uniform Convergence - The Case of Infinite H, The Concept of 'Shatter' and VC Dimension, SVM Example, Model Selection, Cross Validation, Feature Selection
Note: This course is offered by Stanford as an online course for credit. It can be taken individually, or as part of a master’s degree or graduate certificate earned online through the Stanford Center for Professional Development. This course provides a broad introduction to machine learning and statistical pattern recognition. Topics include: supervised learning (generative/discriminative learning, parametric/non-parametric learning, neural networks, support vector machines); unsupervised learning (clustering, dimensionality reduction, kernel methods); learning theory (bias/variance tradeoffs; VC theory; large margins); reinforcement learning and adaptive control. The course will also discuss recent applications of machine learning, such as robotic control, data mining, autonomous navigation, bioinformatics, speech recognition, and text and web data processing. Prerequisites: Knowledge of basic computer science principles and skills, at a level sufficient to write a reasonably non-trivial computer program; familiarity with basic probability theory; familiarity with basic linear algebra.
One of the world's leading universities, Stanford was founded in 1885 in what is now Stanford, California. It is comprised of seven schools, four of which are devoted exclusively to graduate education. Stanford's most renowned programs include the Graduate School of Business, Law School, School of Engineering, and School of Medicine. Notable alumni include author John Steinbeck, Supreme Court Justice William Rehnquist, and Google founders Sergey Brin and Larry Page.