Artificial intelligence and machine learning are disrupting fields of technology. We hear about all the latest tech, advanced implementations in various industries every day. These news stories amaze and scare all at the same. It demonstrates what technology can help us to achieve but due to the ambiguity around, we are skeptical about adopting it in our own everyday lives. But once we grasp the concepts that form the core of machine learning and artificial intelligence, we will be able to look at these technologies with new lens and perspective.
Here are eight books we highly recommend to those who want to get started with machine learning and artificial intelligence. These are not academic textbooks. These books ease you into the world of complex technology without scaring you with jargons or incomprehensible explanations.
Author: Peter Flach
It is one of the most comprehensive books on machine learning. Think of it is a practical reintroduction to machine learning. The author takes a more example-oriented approach. It begins with how an email spam filter works which puts things in perspective for the reader. As the book progresses, Peter Flach introduces you to increasingly complex concepts of machine learning. It’s a great book if you want to get started with machine learning and the math behind it.
Author: Peter Harrington
This book is a mixtape of the foundational theories of machine learning and practical usage of the tools required for analyzing data. Unlike Peter Flach who uses a lot of math in his book, Peter Harrington uses code to demonstrate how programs can be built and algorithms can be deployed. This covers the various stages in building an AI system namely classification of data, forecasting, analyzing, etc. The book is simple and easy to read. It is aimed at introducing to the basics and not necessarily making you an expert in the field of machine learning.
Author: Kevin Murphy
Well, this book would not make for an introductory text to machine learning because this would require that the reader have some introductory-level college math background and know about probability theory. However, it makes for a good modern reference book on machine learning. Kevin Murphy has written this book in an informal style that making it accessible to the reader. It is packed with pseudo-code for most of the important machine learning algorithms out there. The best part all the topics are supported with color images and worked examples drawn from application domains.
Authors: Ian Goodfellow, Yoshua Bengio, and Aaron Courville
This book is a compilation of background on deep learning, its applications, and research topics. The book covers concepts around linear algebra, probability theory and information theory, numerical computation, and machine learning. It walks you through deep learning techniques such as deep feedforward networks, regularization, optimization algorithms, convolutional networks, sequence modeling, and practical methodology. It is a theoretical book recommended for undergraduate or graduate students who wish to kick start a career in machine learning.
Author: Tariq Rashid
A bestseller, this book does not require you to have prior knowledge on the subject. It helps you do what it says on its title. It gives you a step-by-step walk through of the math of neural networks. This in fact helps you create your own neural network using the programming language Python. Once you put this book down, you will be able to write Python code, create and train your own neural networks. Think of it as a ‘fun and unhurried’ journey towards getting familiar with neural networks.
Author: Aurelien Geron
This book teaches you the tools and concepts required for building artificial intelligence systems. It’s a compilation of a minimal theory, application of concrete examples, and two pre-built Python production infrastructures namely scikit-learn and TensorFlow. By the end of the book, you will have learnt techniques such as simple linear regression, progression, and deep neural networks.
Author: Marcos Lopez de Prado
Big data needs to be easily controlled by the machine learning algorithms. And this book teaches you how to structure Big data precisely that way. You also get to know how to do research using machine learning algorithms, back test your discoveries, and avoid false positives. It explains why certain assumptions about machine learning that are applied to the financial world are incorrect. The author uses formal mathematics to evidence these explanations. He then follows through using practical solutions to the assumptions.
Author: John Brockman
This book is a collection of essays by 175 prominent scientists, philosophers, and artists who try to answer the question: what to think about machines that think. It explores different perspectives and aspects around intelligent machines such as morals, control, bias, rights, and classification of these machines. Though the book does not offer concrete answers to such questions, the book floats opinions and ideas about these questions.
Do you have a favorite that you’d like to see included in this list? Let us know in the comments below.