Before engaging specifically in machine learning, we recommend reading the books

• Stewart Russell, Peter Norvig Artificial intelligence. Modern approach source

• George F. Luger Artificial intelligence. Strategies and methods
  for solving complex problems source

In this way, you will have a clearer understanding of the subject area. learning and greatly expand your horizons. Neural networks occupy an important position in machine learning, so it is worth reading the book

• Simon Highkin Neural networks. Full course source

You should also be able to perform preliminary data analysis to understand what machine learning methods can be applied to your data set or how to better prepare it. books:

• Boris Mirkin Introduction to data analysis. Tutorial and workshop source

• Marina Arkhipova, Tatiana Dubrova Data analysis. Tutorial source

• Zagoruiko N. G. Applied methods of data and knowledge analysis source

• Mosteller F., Tukey J. Data analysis and regression source

• Ruban A. I. Data analysis methods

• Wes McKinney Python and data analysis source (practice)

• Robert I. Kabakov R in action. Data analysis and visualization in R source (practice)

You should know well mathematics (especially linear algebra), statistics, probability theory, and discrete mathematics. math. I, for example, do not know math well and it is very difficult for me to read standard textbooks designed for the fact that the teacher will be able to chew up a stingy description of the formula, so for an easy entry threshold, I recommend the following books (from the basics and above):

• Stephen H. Strogac The pleasure of x. A fascinating excursion into the world of mathematics from one of the best teachers in the world source

• Yuri Shikhanovich Introduction to modern Mathematics. Initial concepts source

• Ronald L. Graham, Donald Erwin Knuth Concrete math. Mathematical foundations of computer science source

• Yuri Pukhnachev Mathematics without formulas book1, book2

• Tarasov L. V. The ABC of mathematical analysis. Conversations about basic concepts. Tutorial source

• Anatoly Myshkis Lectures on higher mathematics source

• Richard Courant, Herbert Robbins What is mathematics? source

Then you can take up the standard textbook of mathematical analysis

• Fichtenholz G. M. Fundamentals of mathematical analysis source

Books in Russian language

• Peter Flach Machine learning source, Table of contents and excerpts from chapters

• Christopher M. Bishop Image recognition and machine learning source

• James G., Whitton D., Hastie T., Tibshirani R. Introduction to statistical learning with examples in R source, Table of contents and excerpts from chapters

• Sebastian Rashka Python and machine learning source

• Henrik Brink, Joseph Richards Machine learning source

• Charalambos Marmanis, Dmitry Babenko Intelligent Internet algorithms. Advanced methods of data collection, analysis and processing source

• K. V. Vorontsov Mathematical models case-based learning methods (machine learning theory) source

• Merkov A. B. Introduction to statistical learning methods source

• Arkady Gelig, Alexey Matveev Introduction to the mathematical theory of trainable recognition systems and neural networks. Training manual source

• Merkov A. B. Construction and training of probabilistic models source

• Richart V., Coelho P. L. Building machine learning systems in Python source, Table of contents and excerpts from chapters (here is more practice on machine learning)

• Vyugin V. Mathematical foundations of machine learning and forecasting source

• Chervonenkis A. Ya. Learning theory machines

• Richard S. Sutton, Andrew G. Barto Reinforcement learning source

• Andreas Muller, Sarah Guido Introduction to Machine Learning with Python. A guide for data scientists source

• Davy Silenus, Arno Meissman Fundamentals of Data Science and Big Data. Python and Data Science source

• Lepsky A. E., Bronevich A. G. Mathematical methods of pattern recognition: A course of lectures source

• V. I. Donskoy Algorithmic models of classification training:justification, comparison, choice source

• Mestetsky L. M. Mathematical methods of pattern recognition Course of lectures source

• Christopher D. Manning, Prabhakar Raghavan Introduction to Information Search source

• Jure Leskovets, Anand Rajaraman Analyzing large data sets source: , table of contents and excerpts from chapters

• Goodfellow J., Benjio I., Courville A. Deep learning source, table of contents and excerpts from chapters

• Schlesinger M. I. Ten lectures on statistical and structural pattern recognition source

• Jully A., Pal S. Keras Library-a deep learning tool source: table of contents and excerpts from chapters

• Chardin B., Massaron L., Boschetti A. Large-scale machine learning with Python source table of contents and excerpts from chapters

• Shitikov V. K., Mastitsky S. E. Classification, regression, and other Data Mining algorithms using R source , electronic version

• J. R. R. Tolkien Vander Place Python for complex tasks. Data science and machine learning source

• Darren Cook Machine learning using the H2O library source table of contents and excerpts from chapters

• OpenDataScience Open Course on Machine Learning source - articles on Habrahabr

• Slides of lectures on the course "Machine learning" source

• Lecture 2008 N. Y. Zolotykh How are machines trained? source, presentation for lectures from 2018

• Tariq Rashid Creating a neural network source

• Nikolenko S. I., Kadurin A. A., Arkhangelskaya E. O. Deep learning source

• S. I. Nikolenko, A. L. Tulupyev Self-learning systems source

• Patterson J., Gibson A. Deep learning from a practitioner's perspective source: , table of contents and excerpts from chapters

• Heidt M. Learning about pandas source: , table of contents and excerpts from chapters

• Aurelien Geron Applied machine learning using Scikit-Learn and TensorFlow. Concepts, tools, and techniques for creating intelligent systems source: , table of contents, excerpts from chapters

• P. E. Ovchinnikov The use of artificial neural networks for signal processing. Educational and methodical manual. 2012 source

• Francois Chollet Deep learning in R source: , table of contents, excerpts from chapters

• O'Neill, Shutt Data Science. Insider information for beginners. Including the R language source

• Shai Shalev-Schwartz, Shai Ben-David Machine learning ideas training courses source: , table of contents and excerpts from chapters

• Francois Chollet Deep learning in Python source

• Pratik Joshi Artificial Intelligence with Python examples source

• Bengforth B., Bilbro R., Ojeda T. Applied analysis of text data in Python. Machine learning and building natural language processing applications language source

• Kelleher J., McNamee B., d'Arcy A. Fundamentals of machine learning for analytical forecasting: algorithms, working examples, and case studies source

• Ravichandiran S. Deep learning with reinforcement in Python. OpenAI Gym and TensorFlow for pros source

Video in Russian

• High School economy "Introduction to Machine Learning" source Coursera

• Specialization Machine learning and data analysis including 6 courses : source Coursera

• Video lectures of the course "Machine Learning" from the Yandex School of Data Analysis source on Yandex or source on YouTube

• Specialization Data Analysis from Stepik (part of courses from this specialization is displayed here)

• The course of R. V. Shamin Machine learning and artificial intelligence in mathematics and applications source

• Victor Kantor MIPT Machine learning source

• Course from Stepik Neural networks source

• Video lectures (13 pcs.) Introduction to Data Analysis source Mail.ru

• Video lectures (1 semester) Data Minig source Mail.ru

• Video lectures (2nd semester) Data Minig source: Mail.ru

• Computer Science Center Machine learning, part 1 (fall 2016) source youtube

• Computer Science Center Machine learning, part 2 (spring 2017) source youtube

• Data Mining in Action 10 ML lectures source youtube

• Computer Science Machine Learning Training Sessions source youtube here people share their real experience in ML

• Shamin R. V. Lectures on artificial intelligence and machine learning source

• Artificial intelligence and machine learning (lectures) source-site, youtube

• OpenDataScience channel on Machine Learning and MLClass source youtube

• Sergey Nikolenko Fundamentals of Bayesian inference source youtube

• Technostream Mail.Ru Neural networks in Machine Learning (Fall 2017) source

• Andrey Sozykin Online course Programming deep neural networks in Python source website, youtube

• Biopharmcluster "Severny" Machine learning 11 lectures on ML source YouTube, unfortunately there is no separate playlist, so you will have to search for lectures that are not found through the search in the general playlist yourself.

• 9-week course from the HSE and Yandex Practical Reinforcement Learning (you can find the videos of lectures and practical seminars in Russian in the Materials section of each week) source github

• Information search (fall 2016) source

• Ivakhnenko A. A. Introduction to Neural Network Theory and Deep Learning source

• Python for data analysis source Coursera

• JetBrains Research Machine Learning Seminars source

Online courses, video courses in mathematics and statistics

• Higher School school of Economics, course Linear algebra source Coursera
• Lectorium Linear algebra and analytic geometry source youtube
• MIPT Lecture Hall Linear algebra source
• MIPT, course Probability theory for beginners source: Coursera
• MIPT, course Math for everyone source Coursera
• Course from Stepik Fundamentals of statistics part1, part2, part3
• Course from Stepik Mathematical statistics source
• Course from Stepik Introduction to Discrete Mathematics source
• Course from Stepik Educational program in discrete mathematics source
• Course from Stepik Introduction to Mathematical Analysis source
• Course from Stepik Mathematical analysis part1, part2
• Course from Stepik Data analysis in R part1, part2
• Computer Science Center Data analysis on R in examples and problems (spring 2016) source youtube
• Computer Science Center Data analysis on R in examples and problems, part 2 (spring 2017) source youtube
• YouTube channel Fundamentals of data analysis source
• KhanAcademyRussian Theor. probability and combinatorics source youtube
• Algebra (133video) source KhanAcademyRussian
• R. V. Shamin. Mathematical analysis-lectures source
• circle from the MPMI MIPT School of Deep Learning youtube, github, git2

For an amateur:

• Entertaining statistics. Manga. http://dmkpress.com/catalog/computer/statistics/978-5-94120-269-0

• Interesting statistics. Regression analysis. Manga http://dmkpress.com/catalog/computer/statistics/978-5-97060-115-0

• Entertaining math. Derivatives and integrals. Manga http://dmkpress.com/catalog/manga/978-5-94120-228-7/

• Interesting statistics. Factor analysis. Manga http://dmkpress.com/catalog/computer/statistics/978-5-97060-116-7

Statistics, probability theory:

• Gnedenko B. V., Khinchin A. Ya. An elementary introduction to Probability theory source

• Vladimir Savelyev Statistics and seals source, read a little

• Sarah Boslaf Statistics for all source

• Charles Whelan Bare statistics. The most interesting book about the most boring science source

• Andrew Bruce, Peter Bruce Practical statistics for Data Science specialists source: , table of contents and book fragment

• J. R. R. Tolkien Hey Introduction to Bayesian statistical inference methods source

• Downey A. B. Bayesian models source, table of contents and excerpts

The list will be updated periodically.

Top best free books on Machine learning:

• The Elements of Statistical Learning: Data Mining, Inference, and Prediction. In this book, the authors have tried to combine many important new ideas related to statistical learning. Although the book lacks mathematical details, the authors explain the basics of the concepts quite well. The book is useful not only for statisticians, but also for people working in related fields. areas.

• Introduction To Machine Learning. The purpose of this book is an introduction to inductive logic programming, a branch of science at the intersection of machine learning and logic programming. The book will be useful for those who study the principles of working with databases, data engineering, AI, machine learning and logic programming.

• Reinforcement Learning: An Introduction. Reinforcement learning is one of the ways in which machine learning works. the test system interacts with a certain environment and strives to get the maximum reward for its actions. This book examines the key aspects of this type of training, its history and scope. The threshold for entering this book is only a basic level of knowledge of the principles of the probabilistic model.

• Information Theory, Inference, and Learning Algorithms. This book covers information theory and statistical inference. These topics are at the heart of such areas modern science, such as communication, signal processing theory, data mining, machine learning, bioinformatics, cryptography, and many others. The authors successfully combine theoretical explanations with practical examples and tasks.

• Gaussian Processes for Machine Learning. This book focuses on Gaussian processes and the issue of learning with a teacher. The book contains a lot of algorithms, and also understands the scope of GP applications in machine learning and statistics, for example, in the support method. vectors, neural networks, splines, and so on.

• Bayesian Reasoning and Machine Learning. This book is useful for senior students with a small amount of knowledge in linear algebra and matanalysis. The material in the book goes from simple to complex, using graphical models.

• A Course in Machine Learning. This book provides a set of introductory materials on most of the main aspects of machine learning (learning with and without a teacher, probabilistic modeling, learning theory, etc.).

• Machine Learning, Neural and Statistical Classification. The purpose of this book is to talk about modern approaches to classification. They are compared by performance and application areas in real-world cases. As the name suggests, there are three such approaches: the statistical method, the machine learning method, and the neural network method.

• Introduction To Machine Learning. This book covers many important issues. training since 2006. This is neither a textbook nor a problem book: the purpose of the book is to prepare the reader for further development of this topic.

• Real-world Machine Learning. Henri Brink, Joseph W. Richards, Mark Fetherolf in this book, the authors try to show the practical application of machine learning in everyday tasks, give examples of their solutions and collect all the important knowledge for the beginner.