Lab's recommendation: Awesome books to learn machine learning and AI (continue updating)

Machine Learning in Action (MLiA)

This is an old book, which was published ten years ago, in 2012. The author is Peter Harrington. At that time, there is not so popular ML tools like scikit learn or the DL framework like TF, and Pytorch. This book describes the ML concept and the necessary formula to understand the learning algorithms. Most importantly, the author gives the implementation bit by bit (not just call API) for the algorithms. These can get the reader a deep understanding of how the models/algorithms work and are built. It's super helpful! This book is good for beginner or intermediate readers. But please forget that the top 10 models in ML as the book says, actually there is no best one but just a suitable one.  Also, there is a GitHub repo for the code (though I think could dirt your hands following the book and get the best learning).  The code is in python 2, a popular version a decade ago (currently has stopped the support to python 2). I do not test the code in py 3, while I used py 2 10 years ago. I think most of the code could be used under python 3, might some necessary changes will be needed. 

ps: The cover illustration is interesting and attracts me too. Later I'll write a separate blog to describe the cover illustrations. 

Pattern Classification

This book is a classic one for learning about matching learning, statistical learning, and pattern recognition. The first version was published in 1973, which included pattern classification and scene analysis. The second version was published in 2001 and only focused on pattern classification theory. The authors talked about the changes in the preface. 

The book contains a general guide on the workflow for model development. Also, it contains a detailed theory on classification theory. For this, 

1. both supervised and unsupervised learning is discussed in the book,
2. parametric and non-parametric methods are covered,
3. Metric and nonmetric models for classification,
4. and also include some content in statistical learning 
5. especially a detailed discussion on neural networks (some tricks to train the model)

Hands-On Machine Learning with Scikit-Learn Keras and Tensorflow

This book (version 1 and version 2) could be powerful in learning machine learning and deep learning in action. The first part is for the machine learning using scikit-learn. While the second part is for deep learning using TensorFlow 2.0 (adapted to TF2.0 in version 2). This book gives detailed descriptions of some theories and the popular models' implementations, especially in TF2.0. It's a good guide to starting TF2.0 and to learning ML/DL. 

ps: I like the book cover, and it's a series from O'REILLY for such tech books. Later, I'll do a bit more description for the cover story. 😂

Deep Learning

The book 'Deep Learning could be the first to introduce the popular 'Deep Neural Network (DNN)'. The authors are Ian Goodfellow, Yoshua Bengio and Aaron Courville. Three parts are in the book, the first is the prior knowledge about math and machine learning, the second is the DNN, and the final is research topics in DNN. The book includes many references and introduces more background to readers along with the DNN. I learned the theoretical approach for DNN and the interesting and exciting research topics. Most of the issues are widespread and still open questions to find better solutions. It is worthy of reading many times.

The open file is here.

The cover is generated by Deep Dream.

Computer Vision: A Modern Approach

The second version is published in 2012. This book is still one of the most popular books for learning about different computer vision topics. I like the structure, which is clear for the early, mid, and high-level vision. Also, a very helpful reference to get concepts at the top level to learn CV in general.

Foundations of Statistical Natural Language Processing

It is a classic book for learning natural language processing. It is published in 1999 and then printed six times till 2003. It focuses on natural language knowledge while also containing the statistical side to process NLP, such as classification and clustering.