[1.1机器学习概述.pptVIP

* * * * * * * * 机器学习：新一代计算机技术的浪潮 从浅层学习到深度学习-Lecun G. Hinton：(A) The twodimensional codes for 500 digits of each class produced by taking the first two principal components of all 60,000 training images. (B) The two-dimensional codes found by a 784-1000-500-250-2 autoencoder. For an alternative visualization, see (8). Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile . Copyright 2004-2011 Aspose Pty Ltd. 深度学习的应用 人工智能 机器人与自动化 智能交通 模式识别 智慧城市与家居 Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile . Copyright 2004-2011 Aspose Pty Ltd. 提纲 机器学习的定义 机器学习的目的 机器学习的一般步骤 机器学习的输入 机器学习：新一代计算机技术的浪潮 机器学习 vs. 数据挖掘vs.统计学习 机器学习的相关期刊会议 Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile . Copyright 2004-2011 Aspose Pty Ltd. Machine learning vs Statistics 机器学习vs统计理论 If forced to point out a single difference of emphasis, it might be that statistics has been more concerned with testing hypotheses, whereas machine learning has been more concerned with formulating the process of generalization as search through possible hypotheses. But, this is a gross oversimplification: statistics is far more than hypothesis testing, and many machine learning techniques do mot involve any searching at all. 传统的统计理论侧重于假设检验，机器学习侧重寻找可泛化的模型 Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile . Copyright 2004-2011 Aspose Pty Ltd. 数据挖掘 监督学习 无监督学习 关联规则 数据处理技术 机器学习vs数据挖掘 半/弱监督学习 机器学习 Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile . Copyright 2004-2011 Aspose Pty Ltd. 提纲 机器学习的定义 机器学习的目的 机器学习的一般步骤 机器学习的输入 机器学习：新一代计算技术的浪潮 机器学习 vs. 数据挖掘vs.统计学习 机器学习的相关期刊会议 Evaluation only. Created with Aspose.Slides for .NET 3.5 Client Profile . Copyright 2004-2011 Aspose Pty Ltd. 机器学习的参考书、期刊与会议 参考书： 1.Machine Learning, Tom M. Mitchell, Publisher: McGraw-Hill Science. 中文版：《机器学习》，Tom Mitchell，曾华军 等（译），机械工业出版社，2003年. 2．Machine Learning: a Probabilistic Perspective by Kevin Patrick Murphy 3．斯坦福大学，Andrew N.G. 机器学习开放