DATA 5200 - Statistical Learning 3

DATA 5200 Statistical Learning. (3) This course provides the statistical learning theory. It provides the theoretical basis for many of today’s machine learning algorithms. It covers the approaches to learning problems, estimation of the probability measure and problem of learning, conditions for consistency of empirical risk minimization principle, bounds on the risk for indicator loss functions, structural risk minimization principle, stochastic ill-posed problems, estimating the values of function at given points, perceptron and their generalization, support vector methods for estimating indicator and real-valued functions, and support vector machines for pattern recognition. Prerequisite(s): Prerequisite: DATA 5050.