Summary:At present, there are a lot of AI books on the market. As an AI enthusiast, how to select the book list? At the beginning of the new year, KDnuggets compiled a list of AI books for you to use.
Original: hyperai super nerve
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 directions. The authors of the books are also top scholars and researchers from the field of artificial intelligence.
Whether you’re a beginner in artificial intelligence or have mastered the relevant technology, there’s always one of these books on the list for you. All books can be read online for free, which is very nice.
Introduction: This is a practical book,Focus on data science and machine learning model using python.It well explains the relevant theories, and introduces the necessary mathematical operations according to the needs, so it lays a good rhythm for the whole article.
Introduction: text mining is a kind of computer processing technology to extract valuable information and knowledge from text data, and it is also a hot topic in natural language processing.
This book mainly introduces the text mining and analysis of clean data, all the code is based on R language, which is very good for R language novice.
The book is divided into nine chapters, which introduces how to use r-based tools for text analysis. Clean data has a simple and novel structure, and its analysis will be more effective and easier.
Introduction:This book is edited by Professor Miguel Hernan and Jamie robins of Harvard University. It systematically expounds the concept and method of causal reasoning.This book has been highly praised in Zhihu and other major platforms, and it is a book that many metrologists have been looking forward to for a long time.
Causal reasoning is a complex, all encompassing subject, but the authors of this book do their best to condense the most important basic aspects they think into about 300 pages. If you are interested in building your own conceptual base, this book may be your first choice.
Introduction: this book introduces the concept of statistics in the second chapter,Starting from this chapter, these concepts are interdependent and lead to more advanced topics, such as statistical inference, confidence interval, hypothesis testing, linear regression, machine learning, etc.
The sponsor said that this is the resource he has been waiting for. He has been trying to learn Julia’s data science effectively in the way he always wanted. I hope it’s also to your taste.
Introduction: in many contemporary books, data science has been simplified as a series of programming tools. If you master these tools, they are expected to complete data science for you.
For a long time, other books seem to have little emphasis on the basic concepts and theories of code separation. This book is a good example of the opposite trend, no doubt,This book will provide you with solid basic knowledge and necessary theoretical knowledge for your data science career.
Introduction: once the impact of math heavy theory disappears,You’ll find that topics ranging from partial variance trade-offs to linear regression, model validation strategies, model promotion, kernel methods, and all the way to prediction problems are thoroughly addressed.The advantage of such thorough processing is that your understanding will be deeper than just mastering Abstract intuition.
Introduction: this book starts from describing NLP, introduces how to use Python to perform some NLP programming tasks, and how to access natural language content for processing, and then turns to broader concepts, including concept (NLP) and programming (Python).
Soon,It involves classification, text classification, information extraction and other topics that are usually considered as classic natural language processing.
After learning the basics of NLP through this book, you can continue to learn more modern and cutting-edge technologies.
Introduction: Jeremy Howard, one of the authors of this book, is the former chairman and chief scientist of big data competition platform kaggle. He’s also kaggle’s champion. He is also the youngest faculty member at singularity University.
The co-author Sylvain is an alumnus of the Higher Normal College in Paris, France, and holds a master’s degree in mathematics from the University of Paris Xi (Orsay, France). So is he fast.ai A former teacher and research scientist of, is committed to making deep learning easier by designing and improving technologies that allow models to train quickly on limited resources.
What makes this book different is that it is “top-down”. It explains everything with real examples.As you build these examples, you’ll go deeper and tell readers how to make their projects better. This means that readers will gradually learn all the theoretical foundations they need in the context to understand its importance and how it works.
The authors say that they have spent many years building tools and teaching methods to make previously complex topics very simple.
Introduction:The book has more than 1200 ratings on Amazon, with an average score of 4.6 (out of 5), which shows that most readers think the book is very useful. Many readers think that,This book is easy to understand, and leads you to use Python language to write simple project code.
The knowledge points mentioned in this book are very simple and easy to understand, which is very suitable for beginners.
Introduction:If you know little about the actual automl, don’t worry. This book begins with a solid introduction to the theme, and clearly lists each chapter that readers should look forward to, which is very important in a book composed of independent chapters.
After that, in the first part of the book, you can read directly about the important topics of contemporary automl and be confident about it, because the book was compiled and edited in 2019. After the first part, we will introduce six tools for implementing these automl concepts.
The last part is the analysis of the series of automl challenges that have existed for several years from 2015 to 2018. During this period, people’s interest in automated methods of machine learning seems to have exploded.
Introduction:This book “deep learning” should not need too much introduction. It is co authored by Ian Goodfellow, yoshua bengio and Aaron Courville, the leading figures in the field of artificial intelligence.Musk once commented: “deep learning, CO authored by three experts in the field, is the only comprehensive book in the field. 」
The structure of this book, the first part introduces the basic mathematical tools and the concept of machine learning, the second part introduces the most mature deep learning algorithm, and the third part discusses some prospective ideas, which are widely considered as the future research focus of deep learning.
Introduction:What’s unique about this book is that,The author adopts the concept of “learning through practice”, and the whole book contains executable code.The author tries to combine the advantages of textbooks (clarity and Mathematics) with the advantages of practical courses (practical skills, reference code, implementation skills and intuition). Each chapter teaches you a key idea through a variety of forms, interwoven prose, mathematics, and a self-contained implementation.
Introduction:The first part of the book covers pure mathematical concepts, with no machine learning at all. The second part focuses on the application of these newly discovered mathematical skills to machine learning problems.
According to the wishes of readers, we can adopt top-down or bottom-up methods to learn machine learning and its potential mathematical knowledge.
Introduction:This book is a high score work on Amazon, written by three statistics professors at Stanford University.
The authors have a way of communicating their expertise. Their approach seems to follow a logical and orderly approach, that is, when readers should learn what. However, individual chapters are also independent, so pick up this book, you can directly enter the chapter of model reasoning, as long as you have understood the previous content of this book.
Introduction:The authors of this book are four professors from the University of Southern California, Stanford University and the University of Washington. They all have statistical backgrounds. This book is more practical than the elements of statistical learning. It gives some cases of using R language.
These books are not only highly praised, but also the original English books are not cheap, ranging from $50 to $100. Now you can read it for free, and if you read it, you will make money~