机器学习第七章1概要1.pptVIP

2003.12.18 Machine Learning-Computational Learning Theory Dr. Ding Overview This chapter presents a theoretical characterization of the difficulty of machine learning problems and the capabilities of the machine learning algorithms This theory seeks to answer questions: Under what conditions is successful learning possible? Under what conditions is a learning algorithm assured of learning successfully? Two frameworks for analyzing learning algorithms The probably approximately correct (PAC) framework Learn from a polynomial number of training examples The number of training examples required for learning The mistake bound framework The number of training errors made by a learner 7.1 Introduction Some problems in machine learning How to identify classes of learning problems that are inherently difficult of easy, independent of the learning algorithm? How many training examples are enough? How is the number of training examples affected if the learner is allowed to pose queries to the trainer? can one characterize the number of mistakes that a learner will make before the target function? Can one characterize the computational complexity of classes of learning problems Although general answers to all these questions are not yet known, fragments of a computational theory of learning have begun to emerge. This chapter presents key results from this theory We focus on the problem of inductively learning an unknown target function some important questions: how many training examples are sufficient, how many mistakes will the learner make before succeeding. It is possible to set quantitative bounds on these measures, depending on attributes of the learning problem such as: The size or complexity of the hypothesis space considered by the learner The accuracy to which the target concept must be approximated The probability that the learner will output a successful hypothesis The manner in which training examples are presented to the learner We will focus on broad classes