Last December, I re-shared a post 15 books for AI. So far, I started learning a bit more about AI. Precisely, I started searching documentaries, books and experts views on AI. When I started watching/learning it. The term Machine Learning arises more often. At some point, I saw the relationship between Artificial Intelligence, Machine Learning and Deep Learning. More often, I had seen the pic (like a circle).
Then over the last few months, I started searching and researching more and more. Finally, I came to know, if you wanna learn AI, simultaneously you should learn Machine Learning and Deep Learning too.
Where and how to start?
Books came to my mind. So, I searched a bit more.
Here comes, 7 books by Tableau.
Machine learning and artificial intelligence are growing fields and growing topics of study. While the advanced implementations of machine learning we hear about in the news might sound scary and inaccessible, the core concepts are actually pretty easy to grasp. In this article, we’ll review some of the most popular resources for machine learning beginners (or anyone just curious to learn). Some of these books will require familiarity with some coding languages and math, but we’ll be sure to mention it when that’s the case.
- “Machine Learning For Absolute Beginners: A Plain English Introduction (Second Edition)” by Oliver Theobald
Author: Oliver Theobald
The title is kind of explanatory, right? If you want the complete introduction to machine learning for beginners, this might be a good place to start. When Theobald says “absolute beginners,” he absolutely means it. No mathematical background is needed, nor coding experience — this is the most basic introduction to the topic for anyone interested in machine learning.
“Plain” language is highly valued here to prevent beginners from being overwhelmed by technical jargon. Clear, accessible explanations and visual examples accompany the various algorithms to make sure things are easy to follow. Some simple programming is also introduced to put machine learning in context.
Authors: John Paul Mueller and Luca Massaron
While we’re going with “absolute beginners,” the popular “Dummies” series is another useful starting point. This book aims to get readers familiar with the basic concepts and theories of machine learning and how it applies to the real world. It presents the programming languages and tools integral to machine learning and illustrates how to turn seemingly-esoteric machine learning into something practical.
The book introduces a little coding in Python and R used to teach machines to find patterns and analyze results. From those small tasks and patterns, we can extrapolate how machine learning is useful in daily lives through web searches, internet ads, email filters, fraud detection, and so on. With this book, you can take a small step into the realm of machine learning.
- “Fundamentals of Machine Learning for Predictive Data Analytics: Algorithms, Worked Examples, and Case Studies” by John D. Kelleher, Brian Mac Namee, and Aoife D’Arcy
Authors: John D. Kelleher, Brian Mac Namee, and Aoife D’Arcy
This book covers all the fundamentals of machine learning, diving into the theory of the subject and using practical applications, working examples, and case studies to drive the knowledge home. “Fundamentals” is best read by people with some analytics knowledge.
It presents the different learning approaches with machine learning and accompanies each learning concept with algorithms and models, along with working examples to show the concepts in practice.
This is more of a practical field guide for implementing machine learning rather than an introduction to machine learning. In this book, you’ll learn about how to create algorithms in machine learning to gather data useful to specific projects. It teaches readers how to create programs to access data from websites, collect data from applications, and figure out what that data means once you’ve collected it.
“Programming Collective Intelligence” also showcases filtering techniques, methods to detect groups or patterns, search engine algorithms, ways to make predictions, and more. Each chapter includes exercises to display the lessons in application.
Here, the word ‘hackers’ is used in the more technical sense: programmers who hack together code for specific goals and practical projects. For those who aren’t well versed in the mathematics, but are experienced with programming and coding languages, “Machine Learning for Hackers” comes in. Machine learning is usually based on a lot of math, due to the algorithms needed for it to parse data, but a lot of experienced coders don’t always develop those math skills.
The book uses hands-on case studies to present the material in real-world practical applications rather than going heavy on mathematical theory. It presents typical problems in machine learning and how to solve them with the R programming language. From comparing U.S. Senators based on their voting records to building a recommendation system for who to follow on Twitter, to detecting spam emails based on the email text, machine learning applications are endless.
Author: Peter Harrington
“Machine Learning in Action” is a guide to walk newcomers through the techniques needed for machine learning as well as the concepts behind the practices. It acts as a tutorial to teach developers how to code their own programs to acquire data for analysis.
In this book you’ll learn the techniques used in practice with a strong focus on the algorithms themselves. The programming language snippets feature code and algorithm examples to get you started and see how it advances machine learning. Familiarity with Python programming language is helpful since it is used in most of the examples.
- “Data Mining: Practical Machine Learning Tools and Techniques” by Ian H. Witten, Eibe Frank, and Mark A. Hall
Authors: Ian H. Witten, Eibe Frank, and Mark A. Hall
In “Data Mining,” the authors focus on the technical work in machine learning and how to gather the data you need from specific mining techniques. They go into the technical details for machine learning, teaching the methods to obtain data, as well as how to use different inputs and outputs to evaluate results.
Because machine learning is ever-changing, the book also discusses modernization and new software that shape the field. Traditional techniques are also presented alongside new research and tools. Of particular note is the authors’ own software, Weka, developed for applied machine learning.
Disclaimer: Tableau does not officially endorse nor profit from any products, or opinions therein, listed in this article and as such this page does not engage with any affiliate link programs. This article is intended purely for educational purposes and the above information about products and publications is made available so that readers can make informed decisions for themselves.