Top 7 Machine Learning Books (Part 2)

Let’s continue our journey towards Machine learning. As promised, this article is the second part of the Machine learning books series and will contain the top 4 books. You can read the first article of the series here.

4. The Elements of Statistical Learning

Intro – This is one of the oldest books on the list, which was published almost 2 decades ago in 2001. Yet, it still is one of the bestsellers in the field.
Objective – The objective of the book is to explain the usage of Machine learning in various fields like medicine, biology, finance, and marketing.
Edition – The current and revised edition is the 9^th Almost all the chapters are revised.
The updated version includes graphical models, random forests, ensemble methods, least angle regression & path algorithms for the lasso, non-negative matrix factorization, and spectral clustering. Even a chapter on methods for “wide” data (p bigger than n), including multiple testing and false discovery rates, is created.
Amazon Kindle offers you a preview of the book. This helps you to decide better if this is the one you are looking for.
Rating – The book has received a combined rating of 4-3/5 from a crowd of more than 1100.
Format – The formats available on Amazon are Hardcover which costs ₹.5,683 and the Kindle edition comes at ₹.2522.
Amazon Review –

“Like the first version, the current one is a welcome addition to researchers and academicians equally… Almost all of the chapters are revised… The Material is nicely reorganized and repackaged, with the general layout being the same as that of the first edition… If you bought the first edition, I suggest that you buy the second edition for maximum effect, and if you haven’t, then I still strongly recommend you have this book at your desk. Is it a good investment, statistically speaking!”

Level – Beginner

3. Neural Networks and Deep Learning

Intro – It’s a free eBook. Provided with the high-quality content, this makes it stand out from the rest since Machine Learning books are usually expensive. So, if you are looking for a pocket-friendly start, this is your path.
Objective – The objective of the book is to lucid take on the biologically inspired programming model i.e., Neural Network which allows the Computer to learn on its own from the observed data, makes this eBook a perfect choice for beginners. Michael Nielsen’s offers a powerful set of techniques for learning in neural networks in order to simplify Deep
Rating – It has received a rating of 4.47/5 from 203 ratings in the Good Reads.

“Thanks to this book, I can finally build my own neural net from scratch, not just run one line of code on tensorflow, caret or keras to get what I need. This is really a great tutorial: all codes provided, step-by-step improvement of an ANN to predict the MNIST dataset, interactive plots to understand the basics of neural nets, etc. It is easy to read, gives some good insights into the historical problems encountered in this field of research and how those problems got resolved. The concepts are very well illustrated. Simply perfect.” – N. Mignan

The overview given by Good reads –“Neural networks and deep learning currently provide the best solutions to many problems in image recognition, speech recognition, and natural language processing. This book will teach you the core concepts behind neural networks and deep learning.”
Format – It is only available in an eBook format. And is free of cost.
Level – Beginners and Intermediate

2. Hands-On Machine Learning with Scikit-Learn and Tensor Flow

Intro – AurÈlien GÈron’s name might be complicated, but his take on the Machine Learning with real-life examples and graphics, sure made the subject understandable.
Objective – The objective of the book is to develop the interest of the reader through real-life Apart from the examples, this book features several training models on topics like vector machines, decision trees, random forests and ensemble methods to practice what one learns. The use of a Tensor flow library is a great way to build and train neural nets.
Format – The book is available on Amazon in 2 formats – Paperback and Kindle Edition.
Cost – The cost of the 2 formats is almost similar. Paperback costs ₹.1275 and the Kindle Edition comes at ₹.1401.
Rating – In terms of rating, this book has a rating of 4.5/5 from Amazon as well as Good Reads. (From 94 ratings).
Edition – This is the 1^st Edition of the book as it was published in 2017.
Review – An Amazon customer review of the book,

“This is one of the best books you can get for someone who is just starting out in ML, in its libraries such as Tensorflow, It covers the basics very good. As a book, it is 5/5
Once you are done with this book, the ideal next step is the “Deep Learning Book By Ian Goodfellow”.

Level – Intermediate

1. The Hundred Page – Machine Learning Book

Intro – The most recent book on the list. Published this year and hit the #1 Bestseller spot in no time. Andriy Burkov’s expert understanding of the complex subject and turning it into simple and comprehensible words are surely the reason this book deserves its spot.The use of dual languages such as Python and R make it even more valuable.Another very unique feature of the book is, ‘First Read, then Pay’.
Yes, it’s the first of its kind where the learner can first read the book online and then if he is pleased and wants to learn further, he can buy the book.
Objective – The Objective of the book is to give as many details possible to the reader in just a hundred Given the complexity of the topic, Burkov has definitely done a marvelous job as readers are actually able to grasp the concept.
Edition – As this book was published recently, this is the 1^st
Format – It is available in 2 formats, as an eBook (Kindle Edition) and as a Hardcover.
Cost – Being at the top of the list, this book has high value. And therefore, it is expensive compared to others. The Kindle Edition costs ₹.3031 whereas the hardcover comes at ₹.4663.

Review – What is something that we all do before buying a book? Look at its reviews, right? Well, here is a review from one of the experts in the field –

“The breadth of topics the book covers are amazing for just 100 pages (plus few bonus pages!). Burkov doesn’t hesitate to go into the math equations: that’s one thing that short books usually drop. I really liked how the author explains the core concepts in just a few words. The book can be very useful for newcomers in the field, as well as for old-timers who can gain from such a broad view of the field.”
– AurÈlien Gèron, Senior AI Engineer, author of the bestseller Hands-On Machine Learning with Scikit-Learn and TensorFlow