Kernel machines are a class of algorithms for pattern analysis that use linear classifiers to solve nonlinear problems. They rely on kernel functions and convex optimization or eigenproblems, and are typically analyzed using statistical learning theory. Kernel methods are computationally expensive for datasets larger than a few thousand examples.
Princeton University
Spring 2019
This introductory course focuses on machine learning, probabilistic reasoning, and decision-making in uncertain environments. A blend of theory and practice, the course aims to answer how systems can learn from experience and manage real-world uncertainties.
No concepts data
+ 21 more concepts