At MentorCruise, we are all about making the most out of the experience of others. As part of that, we've connected and asked dozens of experts and professionals in Machine Learning about their favourite books – and here are the answers.
Understanding the concepts of Machine Learning starts with understanding the fundamentals. On your way to mastery, it's crucial for you to understand how certain concepts were derived, and why things work like they do. Starting with these resources is the best way to do so.
ISL is a fundamental book and popular amongst undergrad and grad students for it's clarity and simplicity with explaining concepts. The math required to understand the book is kept to a minimum, making it unique in its format.
Recommended by Chris Albon, Director of Machine Learning @ Wikimedia
"For students that want to go deep into theory, I usually recommend ESL, which is from the same authors as 'Introduction to Statistical Learning' but much more in-depth. The book is somewhat a bible of the area, and freely available."
Recommended by Raffaele Miele, Head of Data Science & Mentor
Bishop's book on pattern recognition is a classic textbook and staple in Machine Learning. Beimg aimed at grad students, but also at researchers and practitioners, it's no easy lecture, but a truly fundamental course book.
Recommended by Denny Britz, AI Researcher, formerly Google and Stanford
We wrote a book on Mathematics for Machine Learning that motivates people to learn mathematical concepts. The book is not intended to cover advanced machine learning techniques because there are already plenty of books doing this. Instead, we aim to provide the necessary mathematical skills to read those other books.
Recommended by Stephen Gabriel, Mentor, NLP & Data Engineer
Often touted the Deep Learning bible, the Deep Learning book by Goodfellow et. al. is an incredible introduction to basic, as well as advanced principles and methods, which are usually explained from the ground up, written by pioneers of the space
Recommended by Tony Beltramelli, Co-Founder & CEO @ Uizard
Especially for coders coming into the space, Machine Learning and Deep Learning can seem dauntig. This book takes a practical approach to introduce fundamental methods and practises to the reader.
Recommended by the experts and mentors at MentorCruise
At least today, code is our door to building algorithms and complex Machine Learning systems. If you want to invest in becoming a more proficient Machine Learning professional faster, investing in code skills is the way to do so. This is where you can start.
"In my mind, software engineering and ML overlap quite a bit and there's a lot of benefit paying attention to the former for the latter."
Recommended by Jason Antic, Creator of DeOldify
The refactoring book by Martin Fowler is a guide on how to transform code with safe and rapid process, vital to keeping it cheap and easy to modify for future needs.
Recommended by Jason Antic, Creator of DeOldify
Python is not the only option! The goal of “R for Data Science” is to help you learn the most important tools in R that will allow you to do data science.
Recommended by Meg Risdal, Product Manager @ Kaggle
Machine Learning is no fun if the ideas only live in your head. These books help you with designing real-life Machine Learning algorithms, help you push the limit, take care of any issues you encounter and engineer functioning Machine Learning systems.
The hands-on Machine Learning book is an amazing piece by Aurélien Géron, taking you from the basics of Machine Learning to applying them to real-word scenarios all in one book.
Recommended by the experts and mentors at MentorCruise
"I have to say, fastai's newest book is really good so far. Exactly what you'd expect based on the classes!"
Recommended by Jason Antic, Creator of DeOldify
Grokking Deep Learning teaches you to build deep learning neural networks from scratch! In his engaging style, seasoned deep learning expert Andrew Trask shows you the science under the hood, so you grok for yourself every detail of training neural networks.
Recommended by the experts and mentors at MentorCruise
Natural Language Processing in Action is your guide to creating machines that understand human language using the power of Python with its ecosystem of packages dedicated to NLP and AI.
Recommended by Stephen Gabriel, Mentor, NLP & Data Engineer
Deep learning has transformed the fields of computer vision, image processing, and natural language applications. Thanks to TensorFlow.js, now JavaScript developers can build deep learning apps without relying on Python or R.
Recommended by Tarin Clanuwat, Researcher @ Center for Open Data in the Humanities
Machine Learning comes in many shapes and sizes. The TinyML book is focused on the smallest one: embedded devices and micro-controllers. In this book, you'll learn how to build tiny machine learning models that work on low-powered Arduino microcontrollers, and often only take up a few kilobytes in size.
Recommended by the experts and mentors at MentorCruise
You've got your regressions and classifications in order – time to move on to some advanced and specialized concepts. Machine Learning is evolving every day, and whether it's about making AI systems safer or deploying them at scale, these books can help you master it.
As deep neural networks become increasingly common in real-world applications, the potential to deliberately 'fool' them with data that wouldn’t trick a human presents a new attack vector. This practical book examines real-world scenarios where DNNs—the algorithms intrinsic to much of AI—are used daily to process image, audio, and video data.
Recommended by Dominic Monn, Founder @ MentorCruise and ML @ Doist
Richard Sutton's book on Machine Learning is universally regarded as one of the most fundamental and important pieces on the matter. Reinforcement Learning is quickly becoming a major part of AI innovation, and a good read for any engineer and scientists to go through.
Recommended by Denny Britz, AI Researcher, formerly Google and Stanford
Humans learn best from feedback—we are encouraged to take actions that lead to positive results while deterred by decisions with negative consequences. This reinforcement process can be applied to computer programs allowing them to solve more complex problems that classical programming cannot. Deep Reinforcement Learning in Action teaches you the fundamental concepts and terminology of deep reinforcement learning.
Recommended by the experts and mentors at MentorCruise
It’s now possible to teach a machine to excel at human endeavors such as painting, writing, and composing music. With this practical book, machine-learning engineers and data scientists will discover how to re-create some of the most impressive examples of generative deep learning models.
Recommended by the experts and mentors at MentorCruise
How is it possible to allow multiple data owners to collaboratively train and use a shared prediction model while keeping all the local training data private? In this book, we describe how federated machine learning addresses this problem with novel solutions combining distributed machine learning, cryptography and security.
Recommended by the experts and mentors at MentorCruise
While not specifically aimed at building your skills in building and applying Machine Learning algorithms, learning about the history, development and most importantly early mistakes of AI development are undoubtedly as important as pioneering the way forward. These are the best pieces to do so.
The Enigma tells the life story of Alan Turing, a famous mathematician and early computer scientist from England, who lived and died during the early 1900s. Today, he is considered to be one of the most influential scientists in the areas of artificial intelligence and theoretical computer science.
Recommended by Nicole Williams, VC @ Compound
In The Second Self, Sherry Turkle looks at the computer not as a tool, but as part of our social and psychological lives; she looks beyond how we use computer games and spreadsheets to explore how the computer affects our awareness of ourselves, of one another, and of our relationship with the world.
Recommended by Nicole Williams, VC @ Compound
By exploring common themes in the lives and works of logician Kurt Gödel, artist M. C. Escher, and composer Johann Sebastian Bach, the book expounds concepts fundamental to mathematics, symmetry, and intelligence. It also discusses what it means to communicate, how knowledge can be represented and stored, the methods and limitations of symbolic representation, and even the fundamental notion of 'meaning' itself.
Recommended by Dominic Monn, Founder @ MentorCruise and ML @ Doist
Artificial intelligence does the seemingly impossible, magically bringing machines to life--driving cars, trading stocks, and teaching children. But facing the sea change that AI will bring can be paralyzing. How should companies set strategies, governments design policies, and people plan their lives for a world so different from what we know?
Recommended by the experts and mentors at MentorCruise
Have any other suggestions? Add here.
