Artificial Intelligence, Machine Learning and Deep Learning are all the rage in the press these days, and if you want to be a good Data Scientist you're going to need more than just a passing understanding of what they are and what you can do with them.
They've been around since the 1970s, and until recently have only really been used as research tools in medicine and engineering. Google, Facebook and a few others, though, have realised that there are commercial uses for machine learning algorithms, and so everyone is interested in them again.
These days machine learning algorithms are being used for:
- Data Security & Fraud Detection
- Financial Trading
- Medical Diagnosis
- Marketing & Sales
- Online Search Engines
- Image & Speech Recognition
- Smart Cars & Smart Cities
And the list goes on and on...
If you're not sure how to get started with machine learning, the 3 books in this blog post will help you make your first steps.
Disclosure: the three books in this post link you to the listed book at your local Amazon store. We may earn an affiliate commission for purchases you make when using the links to books on this page.
In this post - the 6th in a series of 8 in which we bring you 21 Inspirational Books for All Aspiring Data Scientists, we highlight 3 books to introduce you to Machine Learning and how it is being used in Data Science:
- Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems
- Introduction to Machine Learning
- Machine Learning for Absolute Beginners: A Plain English Introduction
They are all highly recommended reading and will get your machine learning skills motoring...
Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems
by Aurélien Géron
Through a series of recent breakthroughs, deep learning has boosted the entire field of machine learning. Now, even programmers who know close to nothing about this technology can use simple, efficient tools to implement programs capable of learning from data. This practical book shows you how.
By using concrete examples, minimal theory, and two production-ready Python frameworks – scikit-learn and TensorFlow – author Aurélien Géron helps you gain an intuitive understanding of the concepts and tools for building intelligent systems. You’ll learn a range of techniques, starting with simple linear regression and progressing to deep neural networks. With exercises in each chapter to help you apply what you’ve learned, all you need is programming experience to get started.
- Explore the machine learning landscape, particularly neural nets
- Use scikit-learn to track an example machine-learning project end-to-end
- Explore several training models, including support vector machines, decision trees, random forests, and ensemble methods
- Use the TensorFlow library to build and train neural nets
- Dive into neural net architectures, including convolutional nets, recurrent nets, and deep reinforcement learning
- Learn techniques for training and scaling deep neural nets
- Apply practical code examples without acquiring excessive machine learning theory or algorithm details
by Scott Landschof
Have you ever wondered how Facebook makes money?
It’s FREE for everyone, isn’t it?
Let’s face the disturbing reality: Facebook stores and records everything you do and uses this information to sell you products. Whenever you like a page, open a browser, send a message or add a friend, Facebook stores information about you. If you read the Terms and Conditions form on Facebook you will discover that you authorize full access to all your browser history. If you access your profile on your phone, Facebook can access your GPS to track your locations and all your movements.
All this information Facebook stores about you is then ‘studied’ with extremely complex and sophisticated Machine Learning algorithms. These ‘learn’ about you and your interests, your habits and your patterns. Using this knowledge, Facebook will advertise you products and services that match your unique interests. It knows what you want and it tries to sell it to you, constantly. By selling these uniquely targeted ad spaces Facebook makes money, a lot of it.
Machine Learning is the Answer!
In this book I will teach you about this new and revolutionary approach to computer programming known as Machine Learning. In the first part of the book we will develop an appreciation for the importance and relevance of the field in today’s society. We will seek to answer fundamental questions such as
- Where is machine learning being used today?
- How does Machine Learning impact my life?
- How will machine Learning Shape my Future?
In the second part of the book we will dive into the technical details of machine learning. We will explore the different families of algorithms, the mathematics behind them and how they can be used to solve real problems. The algorithms we will cover are
- Decision Tree Algorithms
- Instance Based Algorithms (eg. K-Nearest Neighbour)
- Regression Algorithms (eg. Logistic Regression)
- Bayesian Algorithms (eg. Naïve Bayes)
by Oliver Theobald
Ready to crank up a virtual server to smash through petabytes of data? Want to add ‘Machine Learning’ to your LinkedIn profile?
Well, hold on there...
Before you embark on your epic journey into the world of machine learning, there is a lot of basic theory to march through first.
Machine Learning for Absolute Beginners has been written and designed for absolute beginners.
It opens with a general introduction to machine learning from a macro level. The second half of the book is more practical and dives into introducing specific algorithms applied in machine learning, including their pros and cons. At the end of the book, I share insights and advice on further learning and careers in this space.
In this step-by-step guide you will learn:
- The very basics of Machine Learning that all beginners need to master
- Association Analysis used in the retail and E-commerce space
- Recommender Systems as you’ve seen online, including Amazon
- Decision Trees for visually mapping and classifying decision processes
- Regression Analysis to create trend lines and predict trends
- Data Reduction and Principle Component Analysis to cut through the noise
- k-means and k-nearest Neighbor (k-nn) Clustering to discover new data groupings
- Introduction to Deep Learning/Neural Networks
- Bias/Variance to optimize your machine learning model
- Careers in the field
All 7 posts in the series:
- 21 Inspirational Books for All Aspiring Data Scientists:
- 3 Great Data Science Books for Aspiring Data Scientists
- 3 Must-Read Statistics Books for Aspiring Data Scientists
- 3 Essential Python Books for Aspiring Data Scientists
- 3 Books on R That all Aspiring Data Scientists Should Read
- 3 Inspirational Machine Learning Books for Aspiring Data Scientists
- 3 Essential Visualisation Books for Aspiring Data Scientists
- 3 Must-Read Books on Data Ethics for Aspiring Data Scientists