Machine Learning: The Art and Science of Algorithms that Make Sense of Data

Machine Learning: The Art and Science of Algorithms that Make Sense of Data by 作者: Peter Flach
ISBN-10 书号: 1107422221
ISBN-13 书号: 9781107422223
Edition 版本: 1
Publisher Finelybook 出版日期: 2012-11-12
Pages: 409
媒体推荐"This textbook is clearly written and well organized. Starting from the basics,the author skillfully guides the reader through his learning process by providing useful facts and insight into the behavior of several machine learning techniques,as well as the high-level pseudocode of many key algorithms." < /br>Fernando Berzal,Computing Reviews作者简介
Peter Flach has more than twenty years of experience in machine learning teaching and research. He is Editor-in-Chief of Machine Learning and Program Co-Chair of the 2009 ACM Conference on Knowledge Discovery and Data Mining and the 2012 European Conference on Machine Learning and Data Mining. His research spans all aspects of machine learning,from knowledge representation and the use of logic to learn from highly structured data to the analysis and evaluation of machine learning models and methods to large-scale data mining. He is particularly known for his innovative use of Receiver Operating Characteristic (ROC) analysis for understanding and improving machine learning methods. These innovations have proved their effectiveness in a number of invited talks and tutorials and now form the backbone of this book.
目录
Prologue: a machine learning sampler;
1. The ingredients of machine learning;
2. Binary classification and related tasks;
3. Beyond binary classification;
4. Concept learning; 5. Tree models;
6. Rule models;
7. Linear models;
8. Distance-based models;
9. Probabilistic models;
10. Features;
11. In brief: model ensembles;
12. In brief: machine learning experiments; Epilogue: where to go from here; Important points to remember; Bibliography; Index.
媒体推荐
“这本教科书写得很清楚，组织起来很好，从基础知识出发，作者巧妙地引导读者通过学习过程，提供有用的事实和洞察力，了解几种机器学习技术的行为，以及许多机器学习技术的高级伪代码关键算法“。 Fernando Berzal，计算机评论
作者简介
Peter Flach在机器学习教学和研究方面有二十多年的经验。他是2009年ACM会议知识发现和数据挖掘以及2012年欧洲机器学习和数据挖掘会议的机器学习和计划联合主席。他的研究跨越机器学习的各个方面，从知识表达和使用逻辑学习到从高度结构化的数据到机器学习模型和方法到大规模数据挖掘的分析和评估。他以创新使用接收机操作特性（ROC）分析为理解和改进机器学习方法而闻名。这些创新已经证明了它们在一些邀请会谈和教程中的有效性，现在已成为本书的骨干。
目录
序言: 机器学习采样器;
机器学习的成分;
二进制分类及相关任务;
超越二进制分类;
概念学习;树模型;
规则模型;
线性模型;
基于距离的模型;
概率模型;
特点;
简而言之: 模特儿组合;
简言之: 机器学习实验;结语: 从这里去哪里要记住的要点参考书目;指数。