ML resources#

Textbooks#

  1. [Hastie, Tibshirani, and Friedman, 2009] (can be downloaded here) is a highly regarded textbook offering comprehensive coverage of statistical learning and machine learning. It provides practical examples and R code for implementation, making it accessible to a broad audience, from beginners to experienced practitioners, and serves as a go-to resource in the fields of statistics and machine learning.

  2. An Introduction to Statistical Learning is more friendly for beginners as less theoretical and more practical version of the previous textbook. There are two versions: With Applications in R and With Applications in Python. Additional resources such as labs, slides, pictures, videolectures are also provided.

  3. [Bishop, 2006] (download link) generally adopts the Bayesian approach to machine learning. It is written in a rigorous mathematical style. Each chapter is supplied by dozens of problems, some of them require quite tough mathematics.

  4. [Murphy, 2022] (more info here) is even heavier relied on probabilistic and Bayesian grounds. It pays special attention to deep learning and its applications, the hottest area of machine learning nowadays. Even more modern advanced topics are covered in the second book Probabilistic Machine Learning: Advanced Topics.

  5. [Prince, 2023] (more info here) is a kind introduction to the modern field of deep learning.

Online books#

  1. ML Handbook from Yandex (in Russian).

  2. Deep Learning Book.

  3. Dive into Deep Learning. Interactive deep learning book with code, math, and discussions.

Online courses#

  1. Maching Learning with Andrew Ng.

  2. Open Machine Learning Course from ODS.

  3. Machine learning course by K. V. Vorontsov (in Russian).

  4. A magnificent NLP Course for You from Lena Voita.

  5. Courses from Hugging Face: NLP, Deep RL, Audio.

Other#