机器学习是人工智能的一个子领域，是人工智能中非常活跃且范围甚广的主要核心研究领域之一，也是现代智能系统的关键环节和瓶颈。机器学习吸取了人工智能、概率统计、计算复杂性理论、控制论、信息论、哲学、生理学、神经生物学等学科的成果，主要关注于开发一些让计算机可以自动学习的技术，并通过经验提高系统自身的性能。本文介绍了机器学习的概念、基本结构和发展，以及各种机器学习方法，包括机械学习、归纳学习、类比学习、解释学习、基于神经网络的学习以及知识发现等，并简单叙述了机器学习的相关算法，包括决策树算法、随机森林算法、人工神经网络算法、SVM算法、Boosting与Bagging算法、关联规则算法、贝叶斯学习算法以及EM算法等，最后还指出了机器学习的应用及其发展趋势。-Machine learning is a subset of the field of Artificial Intelligence,is very active in Artificial Intelligence and a wide range of research in the field of one of the main core, is the key and the bottleneck of a modern intelligent system.Machine Learning has absorbed the results of Artificial Intelligence, Probability and Statistics, Computational Complexity Theory, Cybernetics, Information Theory, Philosophy, Physiology and Neurobiology, and other disciplines.It concerns mainly about how to develop some of technology which can make the computer auto-learning,and through experiences to improve the performance of the system itself.This paper introduces the concept,the basic structure and development of machine learning, and a variety of machine learning methods,including machine learning, inductive learning, learning by analogy, explanation-based learning,based on neural network learning and knowledge discovery, and so on. And briefly descrip the algorithms of machine learning,includin