Machine Learning in Action: Machine Learning in Action: Machine Learning in Action: Machine Learning In Action: Machine Learning System Design: Spark Machine Learning in Action: Mahout In Action: Machine Learning in Action: Test-Driven Development Methods

【 Activity 】 Still send 5 books. Let’s change the rules this time. The top five people with the most liked comments will receive a free book, and the winner will get to choose one of the seven books. Everybody’s free to do what they want, you know… The deadline is 10:00 a.m. on July 28.

PS: Machine Learning is a new book. It has just been released. The English version has received very good reviews.

Of course, big data books are related to machine learning, and our big data books are quite many, if you want to know, you can return to the interface of the subscription number to reply to “big data”.

Introduction 1: Comprehensive classics

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

​

By Peter Flach

Translator: Duan Fei

Page number: 312

  • Hailed as the most comprehensive guide to machine learning ever written by Peter Flach, editor-in-chief of the _Machine Learning_ journal

  • Hundreds of selected examples and illustrative illustrations bring together all the advanced methods used to understand, mine and analyze data

One of the most comprehensive machine learning textbooks on the market to date, this book brings together all the advanced methods for understanding, mining, and analyzing data, and visually and accurately illustrates the principles behind them through hundreds of selected examples and illustrative illustrations. The content covers the components of machine learning and machine learning tasks, logical models, geometric models, statistical models, matrix decomposition, ROC analysis and other hot topics.

Beginner 2: The easiest to get started

Description – raid-duty ト Lucida ぶ mechanistic learning

​

Author: Will Sugiyama

Translator: Xu Yongwei

Page number: 240

  • The simplest introduction to machine learning, 187 graphs easy to start

  • Covers the most classic and versatile algorithms in machine learning

  • Provide executable Matlab program code

In this book, various machine learning algorithms based on the least square method are introduced in detail from the least square method with rich illustrations. The first part introduces the general situation of machine learning field. Part ⅱ and Part ⅲ introduce various supervised regression algorithms and classification algorithms respectively. Part ⅳ introduces various unsupervised learning algorithms. Part ⅴ introduces emerging algorithms in machine learning. Most algorithms in the book have corresponding MATLAB program source code, which can be used for simple testing.

Combat 1: The most popular

Machine Learning in Action

​

By Peter Harrington

Translator: Li Rui, Li Pengqu, Yadong, Wang Bin

Page number: 332

  • Best-selling machine learning book

  • Introduce and implement the mainstream algorithms of machine learning

  • Efficient combat content for daily tasks

The book uses carefully crafted examples to cut into everyday tasks, eschewed academic languages and used efficient reusable Python code to illustrate how to process, analyze, and visualize statistics. Through various examples, readers can learn the core algorithms of machine learning and apply them to strategic tasks such as classification, prediction, and recommendation. In addition, they can be used for more advanced functions such as summarization and simplification.

Practice 2: The Bing team teaches you ML system design

Building Machine Learning Systems with Python

​

By Willi Richert and Luis Pedro Coelho

Translator: Liu Feng

Page number: 224

  • Microsoft Bing core team members launched

  • Focus on how algorithms are written and programmed

  • Learn to solve practical problems with lots of examples

This book will show you how to discover patterns in raw data, starting with Python’s relationship to machine learning, introducing some libraries, and then moving on to more formal project development based on data sets, including modeling, recommendations, and improvements, as well as sound and image processing. With popular open source libraries, we can learn how to efficiently manipulate text, images, and sound. Readers will also learn how to evaluate, compare, and select suitable machine learning techniques.

Field 3: Spark + ML

Machine Learning with Spark

​

By Nick Pentreath

Translator: CAI Liyu, Huang Zhangshuai, Zhou Jimin

Page number: 240

  • When machine learning meets Spark, the most popular parallel computing framework

  • Based on the machine learning algorithm as the main line, the practical application of Spark is discussed with examples

This book covers the basics of Spark, from using the Spark API to load and process data to using data as input to a variety of machine learning models. Common machine learning models, including recommendation systems, classification, regression, clustering, and dimensionality reduction, are explained through detailed examples and real-world applications. Finally, some advanced content is introduced, such as large-scale text data processing, online machine learning and model evaluation methods under Spark Streaming.

Actual Combat 4: Mahout ML

Mahout in Action

​

Authors: Sean Owen, Robin Anil et al

Translator: Wang Bin, Han Jizhong, Wan Ji

Page number: 340

  • Apache Foundation official recommendation

  • The Mahout core team’s masterpiece

  • Actual combat classic of machine learning in the era of big data

Mahout, Apache’s open source machine learning project, condenses core algorithms in the areas of recommendation systems, classification, and clustering into an extensible, off-the-shelf library. Mahout allows you to apply machine learning techniques from companies like Amazon and Netflix to your own projects.

Actual combat 5: Test-driven practice

Thoughtful Machine Learning: A Test-Driven Approach

​

By Matthew Kirk

Translator: Duan Fei

Page number: 204

  • A reliable and stable machine learning algorithm is developed by test-driven method

  • Use machine learning techniques to solve real-world problems involving data

By reading this book, you will be able to:

  • Take a test-driven approach to writing and running tests before writing code

  • Learn the best use of eight machine learning algorithms and weigh them

  • Each algorithm is tested with hands-on, real-world examples

  • Understand the similarities between test-driven development and scientific methods for validating solutions

  • Learn about the risks of machine learning, such as under-fitting or over-fitting of data

  • Explore various techniques that can improve machine learning models or data extraction

Each chapter presents examples of specific data-related problems that machine learning techniques can solve, and how to solve them and process data. It covers test driven machine learning, machine learning overview, K-nearest neighbor classification, naive Bayes classification, hidden Markov model, support vector machine, neural network, clustering, nuclear ridge regression, model improvement and data extraction, etc.

**** — 【 THE END 】 —

This official account all blog posts have been sorted into a directory, please reply “M” in the official account to obtain!

3T technical resources broadcast! Including but not limited to: Java, C/C++, Linux, Python, big data, artificial intelligence, etc. Reply “1024” in the public account, you can get free!!