2021 Book List Recommendations | 15 Highly Rated AI Books, All Free to Read
At present, there are many artificial intelligence books on the market. As an artificial intelligence enthusiast, how should I select the book list? At the beginning of the new year, KDnuggets compiled a list of AI books. Please use it as needed.
KDnuggets, a top website focusing on machine learning, big data, and analytics, recently compiled a list of 15 books covering machine learning, NLP, data science, and other areas. The authors of the books are all top scholars and researchers in the field of artificial intelligence.
Whether you are a beginner in artificial intelligence or already have some experience with related technologies, there is always a book in this list that is suitable for you. All books can be read online for free, which is very nice.
1. Data Science and Machine Learning: Mathematical and Statistical Methods
Authors: DP Kroese, ZI Botev, T. Taimre & R. Vaisman
Introduction: This is a very practical book.There is a strong focus on performing data science and implementing machine learning models using Python.It explains the relevant theories very well and introduces the necessary mathematical operations as needed, thus setting a good pace for the whole article.
Reading address:
2. Text mining: neat tools based on R language
By Julia Silge and David Robinson
Introduction: Text mining is a computer processing technology that extracts valuable information and knowledge from text data. It is also a hot topic in natural language processing.
This book mainly introduces text mining and analysis of tidy data. All codes are written in R language, which is very good for R language novices.
The book is divided into 9 chapters, which introduces how to use tidy tools based on R for text analysis. Tidy data has a simple and novel structure, which makes it more effective and easier to analyze.
Reading address:
https://github.com/dgrtwo/tidy-text-mining
3. Causal Reasoning: What if
Author: Miguel Hernán, Jamie Robins
Introduction:This book, written by Professors Miguel Hernan and Jamie Robins of Harvard University, systematically explains the concepts and methods of causal reasoning.This book has always been highly sought after on major platforms such as Zhihu and is a book that many econometricians have been looking forward to for a long time.
Causal reasoning is a complex, all-encompassing subject, but the authors of this book have done their best to condense what they consider to be the most important basic aspects into about 300 pages. If you are interested in building your conceptual foundation, this book may be the first choice for you.
Reading address:
4. Statistics with Julia: Data Science Foundations, Machine Learning, and Artificial Intelligence
Author: Yoni Nazarathy, Hayden Klok
Introduction: This book introduces statistical concepts in Chapter 2.From this chapter on, these concepts build on each other.It also introduces more advanced topics such as statistical inference, confidence intervals, hypothesis testing, linear regression, machine learning, etc.
The author of the book said that this is the resource he has been waiting for, effectively learning Julia data science in the way he has always wanted, and he hopes it will suit your taste too.
Reading address:
5. Data Science Basics
Authors: Avrim Blum, John Hopcroft, Ravindran Kannan
Summary: In many contemporary books, data science has been reduced to a set of programming tools that, if mastered, promise to do the data science for you.
This book is a great example of going against the trend of other books that seem to emphasize the basic concepts and theories of separation from code.This book will provide you with a solid foundation and the theoretical knowledge necessary to pursue a career in data science.
Reading address:
6. Understanding Machine Learning: From Theory to Algorithms
Author: Shai Shalev-Shwartz, Shai Ben-David
Introduction: Once the potential shock of math-heavy theory has worn off,You will find that topics ranging from the bias-variance trade-off to linear regression, model validation strategies, model boosting, kernel methods, all the way to prediction problems are thoroughly treated.The benefit of such a thorough treatment is that your understanding will be deeper than just grasping abstract intuition.
Reading address:
7. Natural Language Processing with Python
Author: Steven Bird, Ewan Klein, Edward Loper
Introduction: This book starts by describing NLP, introducing how to use Python to perform some NLP programming tasks and how to access natural language content for processing, and then turns to more ambitious concepts, including concepts (NLP) and programming (Python).
soon,It involves classification, text categorization, information extraction, and other topics that are generally considered to be classic natural language processing.
After you learn the basics of NLP through this book, you can move on to more modern and cutting-edge techniques.
Reading address:
8. Deep Learning by Coder using Fastai and PyTorch
By Jeremy Howard and Sylvain Gugger
Introduction: Jeremy Howard, one of the authors of this book, is the former chairman and chief scientist of the big data competition platform Kaggle. He is also a champion of Kaggle. He is also the youngest faculty member of Singularity University in the United States.
Co-author Sylvain is an alumnus of the Ecole Normale Supérieure in Paris, France, and holds a Master’s degree in Mathematics from the University of Paris-Sud (Orsay, France). He is also a former teacher and research scientist at fast.ai, where he works to make deep learning more accessible by designing and improving techniques that allow models to be trained quickly on limited resources.
What makes this book unique is that it is taught from the top down. It explains everything through real examples.As we build on these examples, we'll go deeper and deeper, showing you how to make your projects better and better. This means that you'll learn all the theoretical foundation you need, step by step, in context, to understand why it's important and how it works.
The authors say they have spent many years building tools and teaching methods to make a previously complex subject very simple.
Reading address:
http://50315d5e32ce03ba1773cc0ce6940a86.registreimarcasepatentes.com.br/read/
9. Python for Everyone
By Charles R. Severance
Introduction: This book has more than 1,200 ratings on Amazon, with an average rating of 4.6 (out of 5), which shows that most readers think the book is useful. Many readers think thatThis book explains the concepts in an easy-to-understand way and encourages you to write code for simple projects using the Python language.
The knowledge points mentioned in this book are very easy to understand and very suitable for entry-level learning.
Reading address:
10. AutoML: Methods, Systems, Challenges
Edited by Frank Hutter, Lars Kotthoff, and Joaquin Vanschoren
Summary: If you know little about actual AutoML, don’t worry. The book starts with a solid introduction to the topic and clearly lays out what to expect chapter by chapter, which is important in a book consisting of self-contained chapters.
After that, in the first part of the book, you can jump right in and read about the important topics in contemporary AutoML with confidence, because the book was organized and edited in 2019. After the first part, six tools for implementing these AutoML concepts will be introduced.
The final section is an analysis of the AutoML Challenge series that existed for a few years between 2015 and 2018, a period during which interest in automated approaches to machine learning seemed to explode.
Reading address:
11. Deep Learning
By Ian Goodfellow, Yoshua Bengio and Aaron Courville
Introduction: This book "Deep Learning" should not need much introduction. It is co-authored by Ian Goodfellow, Yoshua Bengio and Aaron Courville, leaders in the field of artificial intelligence.Musk once commented: "Deep Learning is co-authored by three experts in the field and is the only comprehensive book in the field."
The book is structured in such a way that the first part introduces the basic mathematical tools and concepts of machine learning, the second part introduces the most mature deep learning algorithms, and the third part discusses some forward-looking ideas that are widely considered to be the future research focus of deep learning.
Reading address:
https://www.deeplearningbook.org/
12. Dive Into Deep Learning
By: Aston Zhang, Zachary C. Lipton, Mu Li and Alexander J. Smola
Introduction: This book is unique in thatThe author adopts a "learning by doing" philosophy, and the entire book contains runnable code.The authors try to combine the strengths of a textbook (clarity and mathematics) with the strengths of a hands-on tutorial (practical skills, reference code, implementation tips, and intuition). Each chapter teaches you a key idea through multiple modalities, interweaving prose, mathematics, and a self-contained implementation.
Reading address:
13. Mathematical Foundations of Machine Learning
Author: Marc Peter Deisenroth, Aldo Faisal, Cheng Soon Ong
Introduction: The first part of this book covers purely mathematical concepts, without touching on machine learning at all. The second part turns attention to applying these newfound mathematical skills to machine learning problems.
Depending on the reader's preferences, one can take either a top-down or bottom-up approach to learning about machine learning and its underlying mathematics.
Reading address:
14. Basics of Statistical Learning
Author: Trevor Hastie, Robert Tibshirani, Jerome Friedman
Introduction: This book is a high-scoring work on Amazon, and the authors are three statistics professors from Stanford University.
The authors have a way with how they convey their expertise. Their approach seems to follow a logically ordered method of what the reader should learn at what time. However, the individual chapters are also self-contained, so picking up this book, you can jump right into the chapter on model reasoning, as long as you already understand the previous content of the book.
Reading address:
15. Introduction to Statistical Learning: R Applications
Author: Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani
Introduction: The authors of this book are four professors from the University of Southern California, Stanford University, and the University of Washington, all of whom have a background in statistics. This book is more practical than "The Elements of Statistical Learning" and gives some examples implemented in R.
Reading address:
These books are not only highly acclaimed, but also the original English books are not cheap, basically ranging from 50 to 100 US dollars. Now you can read them for free, and you will earn money if you read them~
Sources:
https://www.kdnuggets.com/2020/12/15-free-data-science-machine-learning-statistics-ebooks-2021.html