Большой список актуальных лекций, практик, книг и курсов по машинному обучению.

Бесплатные онлайн-курсы Машинное обучение и анализ данных, актуальных в 2023 году.

• Перечень лучших курсов по практически любым областям математики
• Тонна разнообразных курсов по программированию, алгоритмам, в том числе 29 курсов по ML
• @machinelearning_interview( разбор вопросов с собеседований и практические мл задачи).
• Coursera:
  • CS229: Machine Learning (Andrew Ng, Stanford University) – самый популярный курс по машинному обучению (осторожно, вместо стандартных Питона или R – Matlab/Octave)
  • Специализация Машинное обучение и Анализ данных (Яндекс + МФТИ/MIPT)
    •  мой репозиторий по этой специализации
  • Machine Learning Foundations: A Case Study Approach (University of Washington)
  • Data Mining Specialization
  • Data Science at Scale Specialization (University of Washington)
  • Calculus: Single Variable Part 1 (University of Pennsylvania)
  • Современная комбинаторика (А.М. Райгородский, МФТИ/MIPT)
  • Теория вероятностей для начинающих (А.М. Райгородский, МФТИ/MIPT)
  • Линейная алгебра (ВШЭ/HSE) — курс линейной алгебры для нематематических факультетов, подходит «для быстрого старта»
  • Эконометрика (ВШЭ/HSE) (Econometrics)
  • Business Analytics Specialization (University of Pennsylvania) – специализация о практическом применении статистики и анализа данных. Для людей, разочаровавшихся в DS и не понимающих, на кой это всё
  • Social Network Analysis (University of Michigan)
  • Social and Economic Networks: Models and Analysis (Stanford University)
  • Recommender Systems Specialization (University of Minnesota)
  • Build Intelligent Applications Specialization (University of Washington)
  • Программирование на Python (МФТИ/MIPT)
• Udacity:
  • Machine Learning Engineer Nanodegree (co-created by Kaggle)
  • Data Analyst Nanodegree (co-created by Facebook & MongoDB)
  • Artificial Intelligence Nanodegree (co-created by IBM Watson & Amazon Alexa)
  • Predictive Analytics for Business Nanodegree (co-created by Tableau & Alteryx)
• Edx:
  • Data Science and Engineering with Spark XSeries (Berkeley)
  • 6.002x: Introduction to Computational Thinking and Data Science (MIT)
  • 6.041x: Introduction to Probability – The Science of Uncertainty (MIT)
  • The Analytics Edge (MIT)
• Learning from Data (Caltech) – введение в машинное обучение (основная теория, алгоритмы и области практического применения)
• Видеозаписи лекций Школы Анализа Данных (ШАД)
  • Видеолекции курса «Машинное обучение» (К. В. Воронцов, ШАД)
• Data Mining in Action course materials (МФТИ/MIPT)
• Открытый курс OpenDataScience по машинному обучению
• Intro to Python for Data Science – основы Python и немного про NumPy
• Основы статистики — качественное введение в статистику, целиком на русском языке
• Data Science and Machine Learning Essentials (Microsoft)
• CS231n: Convolutional Neural Networks for Visual Recognition (Stanford University) — отличный десятинедельный курс по нейросетям и компьютерному зрению
  •  repo on github
• Mining Massive Datasets (Stanford University) – курс, основанный на книге Mining of Massive Datasets авторов Jure Leskovec, Anand Rajaraman, and Jeff Ullman (они же являются инструкторами этого курса)
• CS109: Data Science (Harvard University)
• Foundations of Machine Learning — a part of Bloomberg’s Machine Learning EDU initiative

Обзор книг machine learning

Огромный список шпаргалок Data science на все случаи жизни.

Активное обучение

• Active Learning Literature Survey (2010) [B Settles] [67pp]
• Подробный учебный план для подготовки программистов к трудоустройству в Google.

Биоинформатика

• Introduction to Bioinformatics (2013) [A Lesk] [255pp] 📚
• Bioinformatics – an Introduction for Computer Scientists (2004) [J Cohen] [37pp]
• Opportunities and Obstacles for Deep Learning in Biology and Medicine (2017) [T Ching, DS Himmelstein, BK Beaulieu-jones] [102pp]

Классификация

• Supervised Machine Learning: A Review of Classification Techniques (2007) [SB Kotsiantis, I Zaharakis, P Pintelas] [20pp]
• Web Page Classification: Features and Algorithms (2009) [X Qi, BD Davison] [31pp]

Кластеризация

• Data Clustering: 50 Years Beyond K-Means (2010) [AK Jain] [16pp] ⭐
• A Tutorial on Spectral Clustering (2007) [U VON Luxburg] [32pp]
• Handbook of Blind Source Separation: Independent Component Analysis and Applications (2010) [P Comon, C Jutten] [65pp] 📚
• Survey of Clustering Algorithms (2005) [R Xu, D Wunsch] [34pp]
• A Survey of Clustering Data Mining Techniques (2006) [P Berkhin] [56pp]
• Clustering (2008) [R Xu, D Wunsch] [341pp] 📚

Компьютерное зрение

Список лучших (и бесплатных) книг для изучения Машинного Обучения

• Pedestrian Detection: An Evaluation of the State of the Art (2012) [P Dollar, C Wojek, B Schiele] [19pp] ⭐
• Computer Vision: Algorithms and Applications (2010) [R Szeliski] [874pp] 📚 ⭐
• A Survey of Appearance Models in Visual Object Tracking (2013) [X Li] [42pp] ⭐
• Object Tracking: A Survey (2006) [A Yilmaz] [45pp]
• Head Pose Estimation in Computer Vision: A Survey (2009) [E Murphy-chutorian, MM Trivedi] [20pp]
• A Survey of Recent Advances in Face Detection (2010) [C Zhang, Z Zhang] [17pp]
• Monocular Model-Based 3d Tracking of Rigid Objects: A Survey (2005) [V Lepetit] [91pp]
• A Survey on Face Detection in the Wild: Past, Present and Future (2015) [S Zafeiriou, C Zhang, Z Zhang] [50pp]
• A Review on Deep Learning Techniques Applied to Semantic Segmentation (2017) [A Garcia-garcia, S Orts-escolano] [23pp]
• Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017) [D Russo, B VAN Roy, A Kazerouni, I Osband] [67pp]
• Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017) [J Janai, F Güney, A Behl, A Geiger] [14pp]

Лучшие ресурсы машинное обучение

• Календарь соревнований по анализу данных
• @data_analysis_ml -лучшие материалы по анализу данных
• Машинное обучение: вводная лекция – К. В. Воронцов
• Lecture notes and code for Machine Learning practical course on CMC MSU
• 100+ Free Data Science Books – более 100 бесплатных книг по Data Science
• Free O’Reilly data science ebooks
• 100 репозиториев по машинному обучению
• awesome-machine-learning — A curated list of awesome Machine Learning frameworks, libraries and software
• Open Source Society University’s Data Science course – this is a solid path for those of you who want to complete a Data Science course on your own time, for free, with courses from the best universities in the World
• Доска по data science в Trello — проверенные материалы, организованные по темам (expertise tracks, языки программирования, различные инструменты)
• Machine Learning Resource Guide
• 17 ресурсов по машинному обучению от Типичного Программиста
• 51 toy data problem in Data Science
• practical-pandas-projects — project ideas for improving one’s Python data analysis skills
• Dive into Machine Learning
  •  Dive into Machine Learning repo on github
• Data Science Interview Questions — огромный список вопросов для подготовки к интервью на позицию data scientist’а
• Много книг по Natural Language Processing
• Список открытых источников данных, на которых можно найти бесплатные датасеты
• What should I learn in data science in 100 hours?
• machine-learning-for-software-engineers — A complete daily plan for studying to become a machine learning engineer
• Tutorials on topics in machine learning
• Постоянно обновляющаяся подборка ссылок по датасаенсу
• Teach yourself Machine Learning the hard way!
• An article a week – list of good articles on ML/AI/DL
• The most popular programming books ever mentioned on StackOverflow
• Cookiecutter Data Science – A logical, reasonably standardized, but flexible project structure for doing and sharing data science work
• awesome-datascience-ideas – A list of awesome and proven data science use cases and applications
• machine-learning-surveys – A curated list of Machine Learning Surveys, Tutorials and Books
• A hands-on data science crash course in Python by Bart De Vylder and Pieter Buteneers from CoScale
• docker-setup – A Curated List of Docker Images for Data Science Projects, with Easy Setup
• Notes on Artificial Intelligence – конспекты по разным ML-related темам, от алгебры до Байеса

Глубокое обучение

• Deep Learning (2016) [IJ Goodfellow, Y Bengio, A Courville] [800pp] 📚 ⭐⭐
• Deep Learning in Neural Networks: An Overview (2015) [J Schmidhuber] [88pp] ⭐⭐
• Learning Deep Architectures for Ai (2009) [Y Bengio] [71pp] ⭐
• Tutorial on Variational Autoencoders (2016) [C Doersch] [65pp] ⭐
• Deep Reinforcement Learning: An Overview (2017) [ Y Li] [30pp]
• NIPS 2016 Tutorial: Generative Adversarial Networks (2016) [I Goodfellow] [57pp]
• Opportunities and Obstacles for Deep Learning in Biology and Medicine (2017) [T Ching, DS Himmelstein, BK Beaulieu-jones] [102pp]
• A Review on Deep Learning Techniques Applied to Semantic Segmentation (2017) [A Garcia-garcia, S Orts-escolano] [23pp]
• Deep Learning for Video Game Playing (2017) [N Justesen, P Bontrager, J Togelius, S Risi] [16pp]
• Deep Learning Techniques for Music Generation (2017) [JP Briot, G Hadjeres, F PACHET ] [108pp]

Библиотека ML-специалиста

• A Course in Machine Learning – Hal Daumé III
• A Probabilistic Theory of Pattern Recognition – Devroye, Gyorfi, Lugosi (pdf)
• Applied Predictive Modeling – M. Kuhn, K. Johnson (2013)
• Bayesian Reasoning and Machine Learning – D.Barber (2015) (pdf)
• Core Concepts in Data Analysis: Summarization, Correlation and Visualization – Boris Mirkin
• Data Mining and Analysis. Fundamental Concepts and Algorithms – M.J.Zaki, W.Meira Jr (2014) (pdf)
• Data Mining: Concepts and Techniques – Jiawei Han et. al.
• Data Science For Dummies – Lillian Pierson (2015)
• Doing Data Science
• Elements of Statistical Learning – Hastie, Tibshirani, Friedman (pdf)
• Foundations of Machine Learning – Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar (2012)
• Frequent Pattern Mining – Charu C Aggarwal, Jiawei Han (eds.) (pdf)
• Gaussian Processes for Machine Learning – Carl E. Rasmugit lssen, Christopher K. I. Williams (pdf)
• Inductive Logic Programming: Techniques and Applications – Nada Lavrac, Saso Dzeroski
• Information Theory, Inference and Learning Algorithms – David MacKay
• Introduction to Information Retrieval – Manning, Rhagavan, Shutze (pdf)
• Introduction To Machine Learning – Nils J Nilsson (1997)
• Introduction to Machine Learning – Smola and Vishwanathan (pdf)
• Machine learning cheat sheet – soulmachine (2017) (pdf)
• Machine Learning in Action – Peter Harrington
• Machine Learning, Neural and Statistical Classification – D. Michie, D. J. Spiegelhalter
• Machine Learning. The Art of Science of Algorithms that Make Sense of Data – P. Flach (2012)
• Machine Learning – Tom Mitchell
• Machine Learning – Andrew Ng
• Mining Massive Datasets – Jure Leskovec, Anand Rajaraman, Jeff Ullman
• Pattern Recognition and Machine Learning – C.M.Bishop (2006)
• Probabilistic Programming and Bayesian Methods for Hackers (free)
• A Programmer’s Guide to Data Mining – Ron Zacharski (pdf)
• R in Action
• Reinforcement Learning: An Introduction – Richard S. Sutton, Andrew G. Barto
• The LION Way Machine Learning plus Intelligent Optimization (pdf)
• Understanding Machine Learning: From Theory to Algorithms
• Анализ больших наборов данных – перевод Mining Massive Datasets
• Математические методы обучения по прецедентам (теория обучения машин) – К. В. Воронцов (pdf)
• Машинное обучение — Петер Флах (pdf)
• Методы ансамблирования обучающихся алгоритмов — диссертация А. Гущина (pdf)

Уменьшение размерности

• Dimensionality Reduction: A Comparative Review (2009) [L VAN DER Maaten, E Postma] [36pp]
• Dimension Reduction: A Guided Tour (2010) [CJC Burges] [64pp]

Ensemble Learning

• Ensemble Methods: Foundations and Algorithms (2012) [ZH Zhou] [234pp]
• Ensemble Approaches for Regression: A Survey (2012) [J Mendes-moreira, C Soares, AM Jorge] [40pp]

Metric Learning

• A Survey on Metric Learning for Feature Vectors and Structured Data (2014) [A Bellet] [59pp]
• Metric Learning: A Survey (2012) [B Kulis] [80pp]

Monte Carlo

• Geometric Integrators and the Hamiltonian Monte Carlo Method (2017) [N Bou-rabee, JM Sanz-serna] [92pp]

Multi-Armed Bandit

• Regret Analysis of Stochastic and Nonstochastic Multi-Armed Bandit Problems (2012) [S Bubeck, N Cesa-bianchi] [130pp] ⭐
• A Survey of Online Experiment Design With the Stochastic Multi-Armed Bandit (2015) [G Burtini, J Loeppky, R Lawrence] [49pp]
• A Tutorial on Thompson Sampling (2017) [D Russo, B VAN Roy, A Kazerouni, I Osband] [39pp]

Multi-View Learning

• A Survey on Multi-View Learning (2013) [C Xu] [59pp]
• A Survey of Multi-View Machine Learning (2013) [S Sun] [13pp]

Natural Language Processing

• A Primer on Neural Network Models for Natural Language Processing (2016) [Y Goldberg] [76pp] ⭐
• Probabilistic Topic Models (2012) [DM Blei] [16pp] ⭐
• Natural Language Processing (Almost) From Scratch (2011) [R Collobert] [45pp] ⭐
• Opinion Mining and Sentiment Analysis (2008) [B Pang, L Lee] [94pp] ⭐
• Survey of the State of the Art in Natural Language Generation: Core Tasks, Applications and Evaluation (2017) [A Gatt, E Krahmer] [111pp] ⭐
• Opinion Mining and Sentiment Analysis (2012) [B Liu, L Zhang] [38pp]
• Neural Machine Translation and Sequence-to-Sequence Models: A Tutorial (2017) [G Neubig] [65pp]
• Machine Learning in Automated Text Categorization (2002) [F Sebastiani] [55pp]
• Statistical Machine Translation (2009) [P Koehn] [149pp] 📚
• Statistical Machine Translation (2008) [A Lopez] [55pp]
• Machine Transliteration Survey (2011) [S Karimi, F Scholer, A Turpin] [46pp]
• Neural Machine Translation and Sequence-to-Sequence Models: A Tutorial (2017) [G Neubig] [57pp]

Physics

• Machine Learning & Artificial Intelligence in the Quantum Domain (2017) [V Dunjko, HJ Briegel] [106pp]

Probabilistic Models

• Graphical Models, Exponential Families, and Variational Inference (2008) [MJ Wainwright, MI Jordan] [305pp]
• An Introduction to Conditional Random Fields (2011) [C Sutton] [90pp]
• An Introduction to Conditional Random Fields for Relational Learning (2006) [C Sutton] [35pp]
• An Introduction to Mcmc for Machine Learning (2003) [C Andrieu, N DE Freitas, A Doucet, MI Jordan] [39pp]
• Introduction to Probability Models (2014) [SM Ross] [801pp] 📚

Рекомендательные системы

• Introduction to Recommender Systems Handbook (2011) [F Ricci, L Rokach, B Shapira] [845pp] 📚 ⭐
• Toward the Next Generation of Recommender Systems: A Survey of the State-of-the-Art and Possible Extensions (2008) [G Adomavicius, A Tuzhilin] [43pp] ⭐
• Matrix Factorization Techniques for Recommender Systems (2009) [Y Koren, R Bell, C Volinsky] [8pp] ⭐
• A Survey of Collaborative Filtering Techniques (2009) [X Su, TM Khoshgoftaar] [20pp]

Reinforcement Learning

• Reinforcement Learning in Robotics: A Survey (2013) [J Kober, JA Bagnell, J Peterskober] [74pp] ⭐
• Deep Reinforcement Learning: An Overview (2017) [ Y Li] [30pp]
• Reinforcement Learning: An Introduction (2016) [RS Sutton, AG Barto] [398pp] 📚
• Bayesian Reinforcement Learning: A Survey (2016) [M Ghavamzadeh, S Mannor, J Pineau] [147pp]
• Reinforcement Learning: A Survey (1996) [LP Kaelbling, ML Littman, AW Moore] [49pp]
• Computer Vision for Autonomous Vehicles: Problems, Datasets and State-of-the-Art (2017) [J Janai, F Güney, A Behl, A Geiger] [14pp]
• Deep Learning for Video Game Playing (2017) [N Justesen, P Bontrager, J Togelius, S Risi] [16pp]

Роботы

• Reinforcement Learning in Robotics: A Survey (2013) [J Kober, JA Bagnell, J Peterskober] [74pp] ⭐
• A Survey of Robot Learning From Demonstration (2009) [BD Argall, S Chernova, M Veloso] [15pp]

Semi-Supervised Learning

• Semi-Supervised Learning Literature Survey (2008) [X Zhu] [59pp]

Submodular Functions

• Learning With Submodular Functions: A Convex Optimization Perspective (2013) [F Bach] [173pp]
• Submodular Function Maximization (2012) [A Krause, D Golovin] [28pp]

Трансфер лернинг

• A Survey on Transfer Learning (2010) [SJ Pan, Q Yang] [15pp] ⭐
• Transfer Learning for Reinforcement Learning Domains: A Survey (2009) [ME Taylor, P Stone] [53pp]

Unsupervised Learning

• Tutorial on Variational Autoencoders (2016) [C Doersch] [65pp] ⭐