Machine learning must-see classic material - the latest version of "statistical machine learning (data mining, inference and prediction) core elements" free share

Recommend a statistical machine by Stanford University three chiefs, Trevor Hastie, Robert Tibshirani and Jerome Friedman, wrote a classic study materials "statistical machine learning (data mining, inference and prediction) core elements," the latest edition (2017), the book details the various types of classical machine learning algorithms for machine learning has a certain basis, want in-depth, comprehensive understanding of machine learning algorithms picture of friends , welcome to download.

End annexed address book download.

This book presents

In the past decade, the rapid development of computer and information technology. It followed by fields of medicine, biology, finance and marketing generated a lot of data. How to better understand the strong demand for these data led to new tools, new technology development area of statistics, and spawned a new field of data mining, machine learning, and bioinformatics. Many of these tools have a common basis, but usually expressed in different terms. The book in a common conceptual framework describes the important thinking in these areas. Although this method is statistical, but instead focuses on the concept of mathematics. The book gives many examples of the use of color and with pictures. For anyone statisticians and data mining in science or industry of interest, it should be a very worth reading books. The book coverage is very broad, from supervised learning (prediction) to unsupervised learning.

The book on many topics were discussed comprehensively detail, including neural networks, support vector machines, classification trees and boosting, graphical models, random forest, integrated approach, Lasso minimum angle regression and path algorithm, NMF and spectral clustering and other types of machine learning algorithms . There is also a chapter to a method of "wide" data (p greater than n), including multiple tests and false discovery rate.

Trevor Hastie, Robert Tibshirani和Jerome Friedman是斯坦福大学的统计学教授。他们是这一领域的杰出研究人员：Trevor Hastie, Robert Tibshirani开发了广义加法模型，并写了一本同名的畅销书。Hastie用S-PLUS编写了许多统计建模软件，并发明了主要的曲线和曲面。Tibshirani提出了Lasso，并且是著名书籍《An Introduction to the Bootstrap》的合著者。Friedman是许多数据挖掘工具的共同发明者，包括CART、MARS和projection pursuit。

本书目录