Data Science Resources

For interview preparation and learning

Every Sunday one resource from this list gets a short write-up on Telegram: @data_science_weekly.

Table of Contents:

• Interview Preparation
• Algorithms and Data Structures
• Programming
• SQL
• Machine Learning
• MLOps
• Deep Learning
• Generative AI
• NLP
• Computer Vision
• Graphs
• Reinforcement Learning
• RecSys
• Time Series
• Big Data
• System Design
• Machine Learning System Design
• Math
• Lists of Materials
• Other
• Adjacent

Interview Preparation

Questions

Data Science

• OVER 100 Data Scientist Interview Questions and Answers by Terence Shin
• Data Science Interviews by Alexey Grigoriev
• Data-Science-Interview-Questions by Youssef Hosni
• Data-Science-Interview-Preparation-Resources by Youssef Hosni
• Data science interview questions with answers
• 120 Data Science Interview Questions
• Вопросы для интервью по специальности Data Science
• Interview Questions from interviewquery.com
• Вопросы с собеседовании по машинному обучению
• 100 вопросов для подготовки к собесу Data Science
• The Data Science Interview Book
• Top 100 Data science interview questions
• 100 вопросов c собесов в Data Science и ML
• ML-Interview
• 160+ Data Science Interview Questions

Machine Learning

• Machine Learning FAQ by Sebastian Raschka
• Machine Learning FAQ by X
• Minimum Viable Study Plan for Machine Learning Interviews
• A Guide for Machine Learning Technical Interviews (FAANG Companies)
• Introduction to Machine Learning Interviews Book by Chip Huyen + Answers
• Machine Learning Interviews by Susan Shu Chang
• 100 Machine Learning interview questions 2024
• Crack the top 40 machine learning interview questions

Deep Learning

• Вопросы тестов по курсу «Глубокое обучение» Александр Дьяконов
• 50 Deep Learning interview questions 2024
• 50 Computer Vision interview questions 2024

SQL

• Вопросы с собеседования по анализу данных SQL в 2023 году
• Лучшие вопросы средней сложности по SQL на собеседовании аналитика данных

NLP

• 63 Must-Know LLMs Interview Questions
• 100 вопросов про NLP
• 50 NLP (Natural Language Processing) interview questions 2024
• LLM (ML) Job Interviews - Resources

Programming

• Awesome interview questions repository
• Шпаргалка для технического собеседования
• Моя любимая задача для собеседований по программированию
• Top 100 Python ML Interview Questions

Behavioural interview

Courses

• Grokking the Behavioral Interview
• Rock the Behavioral Interview

Questions

• Популярные HR вопросы
• Awesome Behavioral Interviews
• Amazon Behavioral Interview Questions Guide
• 41 Behavioural Interview Questions You Must Know (Best Answers Included)
• The 50 Amazon Behavioral Interview Questions with Answers
• Behavioural Questions Answered

Mock Interviews and Pieces of Advice

• Валерий Бабушкин:
  • Выпуск 1: Технический директор karpov.courses Кирилл Черепанов
  • Выпуск 2: Артур Кузин, Kaggle Grandmaster, Head of Deep Learning в компании Eqvilent. В прошлом – Head of Computer Vision Platform в SberDevices
  • Выпуск 3: Дарья — ведущий аналитик данных и продуктовый аналитик в X5 Group
• Episode 07: Intro to Behavioural Interviews
• Dan Croitor
• Tips for answering few tricky behavioural interview questions
• How to Answer Top Interview Questions
• Interview Warmup by Google

English

• Как пройти собеседование на английском языке | StarTalk
• Лена Кочева и Таня Дурова - Как эффективно подготовиться к собеседованию на английском
• Как я устроился в Амазон и перестал переживать за свой английский

Home Assignments

• Тестовые задания
• Сборник тестовых заданий для Product Analyst и Data Analyst
• Тестовые задания по DS
• Список тестовых заданий для прокачки

Tips

• How I Got 15 More Data Science Interviews in One Month?
• Как я проходил собеседования на Machine Learning Engineer
• Google ML engineer interview: the only post you’ll need to read
• Amazon Data Scientist Interview Guide
• The Trimodal Nature of Software Engineering Salaries in the Netherlands and Europe
• Гайд по подготовке CV+Portfolio+Self Presentation+Home task
• Методика STAR для прохождения структурированных собеседований
• Гостевое выступление Тати Габрусевой, Staff Machine Learning Engineer, NLP, LinkedIn 25.05.2022
• Полезные ссылки: Как проходить интервью в DS от Айры
• FAANG Interview. Бортовые заметки сообщества
• You should Review These Topics Before Data Science Technical Interview
• Crack the Amazon Data Scientist Interviews | Ex-FAANG Data Scientist by Dan Lee
• Дайджест уходящего года: релокейт в Европу и США, главное о карьере и сверхзанятости
• How I got in to Amazon, Microsoft, Google. All from studying these resources
• Articles, books and videos to help get well-paying tech jobs by TechPays
• How I Cracked the Meta Machine Learning Engineering Interview
• What we look for in a resume by Chip Huyen
• Не принимай оффер в Data Science, пока…
• Стратегия поиска работы за границей: что писать, с кем говорить и к чему готовиться
• Data Science Interview Guide
• Tech Interview Handbook. Free curated interview preparation materials for busy people
• Разбор резюме Data Scientist в прямом эфире
• А как собеседоваться в 2023?
• Amazon, Microsoft, Facebook, Tesla, Lyft — история поиска работы мечты, или «Вредные» советы для карьерного развития
• Как нанимать сотрудников класса А? Выжимка из книги "Who: The A Method For Hiring"
• Your personal guide to Software Engineering technical interviews
• Что делать при отказе на собеседовании?
• FAANG Interview Chronicles. My experience and recommendations
• How to Crack Machine learning Interviews at FAANG!
• How to Find a Data Science Job in 2024 (with experience)
• Applied ML Scientist. Юра — Рыночек 0:10 + Applied ML Scientist. 2 тайм. Юра — Рыночек 2:16 + Домашнее задание vs. Онлайн-кодинг
• Как я готовился к собеседованию на позицию Senior ML Engineer by Zarin Gleb
• How I landed 18 FAANG+ software engineer offers after not interviewing for 5 years
• На что обращать внимание на алгоритмических секциях собеседований
• Что нужно знать, чтобы найти работу, пройти собеседование и выбрать оффер
• Interview Query is the best adaptive learning platform for Data Scientists by Data Scientists
• Как не провалить интервью. Исследование из Стэнфорда о пользе самоуверенности
• Собеседования в ML
• Евгений Смирнов | Десять вопросов, которые нужно задать перед трудоустройством
• Стрим про карьеру, собеседования и бигтех
• Guide to ML Engineer Job Hunting
• ML/Research Engineer interviews 2025

Resources

• На этой странице вы узнаете про Data Science направление в Маркете, наш стек технологий, этапы собеседований и материалы, которые могут пригодиться
• IT-собеседование в Тинькофф
• Материалы для подготовки по машинному обучению от Тинькофф
• Что надо знать сотруднику Цельса?
• Программа Академии Data Science от Тинькофф
• Max Dama's Quant Trading Interview Guide
• Tech Interview Handbook

Courses

• Хочу крутой оффер

Other

• Data Scientist total compensation and salaries in the Netherlands
• Programmer Competency Matrix
• Just know stuff (or, how to achieve success in a machine learning PhD)
• A Guide to Data Roles
• Dropbox Engineering Career Framework
• Nurturing a non-linear career
• Path to Senior Engineer Handbook
• Interview Principals
• The difference between good and great engineers
• Understanding and Cracking Data Science Interviews
• Собеседования от karpov.courses
• Data-Science-Interview-Resources
• Собеседование Data Scientist в Т-Банк: теория + лайфкодинг

Algorithms and Data Structures

Platforms

• LeetCode foundations
  • Leetcode Patterns foundations List of questions with patterns + tips
  • LeetCode Explore foundations
• Codewars
• HackerRank
• CodeAbbey
• CodeRun lang:rus Инструмент для подготовки к очному собеседованию в Яндексе. Задачи очень похожи на те, что будут на интервью.
• Other
• Coderbyte Challenge Library
• CodinGame

Courses

• Algoprog lang:rus
• Яндекс:
  • Основы алгоритмов | Академия Яндекса
  • Бесплатный курс «Подготовка к алгоритмическому собеседованию» от ЯП
  • Курс «Алгоритмы и структуры данных» от ЯП
  • Курс «Алгоритмы и структуры данных поиска»
• Computer Science Center:
  • Алгоритмы: теория и практика. Методы
  • Алгоритмы: теория и практика. Структуры данных
• Подготовься к алгоритмическому собеседованию за 30 недель
• Introduction To Algorithms by MIT foundations
• Algorithms + Data Structures from CS50's Introduction to Computer Science
• Algorithms, Part I (Princeton University, Coursera)
• Grokking the Coding Interview (Educative)

Resources

• Тренировки по алгоритмам от Яндекса:
  • Тренировки по алгоритмам от Яндекса 1
  • Тренировки по алгоритмам от Яндекса 2
  • Тренировки по алгоритмам от Яндекса 3
  • Тренировки по алгоритмам от Яндекса 4
  • Тренировки по алгоритмам от Яндекса 5
  • Интенсив по алгоритмам от Яндекса
• NeetCode. A better way to prepare for coding interviews.
• The Algorithms. Open Source resource for learning Data Structures & Algorithms and their implementation in any Programming Language
• Алгоритмы и структуры данных простыми словами
• Алгоритмика
• Leetcode. Company-wise questions
• Unlocking Algorithm Efficiency: A Comprehensive Guide to Time and Space Complexity
• Data Structures Reference
• An Executable Data Structures Cheat Sheet for Interviews
• Coding Interview Guide
• Algorithmic Thinking
• Algorithm Notes
• Coding Interview University
• Tech Interview Cheat Sheet
• Comprehensive Data Structure and Algorithm Study Guide
• Data Structures & Algorithms by Google
• Design and Analysis of Algorithms
• Algorithms for Competitive Programming
• e-maxx.ru — Алгоритмы

Articles

• Как проходят алгоритмические секции на собеседованиях в Яндекс
• How to effectively use LeetCode to prepare for interviews
• How To Answer Algorithm Interview Questions? The REACTO Method

Books

• Grokking Algorithms. An illustrated guide for programmers and other curious people
• Elements of Programming Interviews in Python: The Insiders' Guide
• Cracking the Coding Interview: 189 Programming Questions and Solutions
• Problem Solving with Algorithms and Data Structures using Python by Brad Miller and David Ranum, Luther College
• Competitive Programmer's Handbook by Antti Laaksonen
• Competitive Programming by Steven Halim
• 50 Algorithms Every Programmer Should Know: Tackle computer science challenges with classic to modern algorithms in machine learning, software design, data systems, and cryptography
• Competitive Programmer's Handbook
• Программирование: теоремы и задачи — Александр Шень

Programming

General

• Exercism
• Public APIs

Clean Code

• Мартин Р. Чистый код: создание, анализ и рефакторинг / Robert C. Martin. Clean Code: A Handbook of Agile Software Craftsmanship
• Стив Макконнелл. Совершенный код. Мастер-класс / Steve McConnell. Code Complete: A Practical Handbook of Software Construction
• Стайлгайд PySpark: как сделать код элегантным

Python

Courses

• CS50’s Introduction to Programming with Python foundations
• CS50’s Introduction to Artificial Intelligence with Python foundations
• Основы Python
• Python: основы и применение
• Программирование на Python
• Поколение Python:
  • Курс для начинающих
  • Курс для продвинутых
  • Курс для профессионалов
• Learn Python (Codecademy)
• Python для тех, у кого лапки
• Добрый, добрый Python
• Инди-курс программирования на Python: Начальный уровень
• Основы Python (karpov.courses)
• Программирование на языке высокого уровня Python

Theory

• Python Tutorial for Beginners (with mini-projects)
• What the f*ck Python! Exploring and understanding Python through surprising snippets
• Comprehensive Python Cheatsheet
• Python Koans. An interactive tutorial for learning the Python programming language by making tests pass
• Full Speed Python. Learning Python using a practical approach
• The Hitchhiker’s Guide to Python!
• A collection of design patterns and idioms in Python
• Python Cheatsheet
• Write faster Python code, and ship your code faster
• PEP 257 – Docstring Conventions
• Threading in Python: The Complete Guide
• multiprocessing — Process-based parallelism

Questions

• 53 Python Interview Questions and Answers
• Python: вопросы на собеседовании:
  • Часть I. Junior
  • Часть II. Middle
  • Часть III. Senior

Other

• Efficient Python Tricks and Tools for Data Scientists
• Python Roadmap (roadmap.sh)

Practice

• Задачи по Python и машинному обучению
• Project Based Learning
• FastAPI Best Practices
• Python Training by J.P.Morgan
• 101 Pandas Exercises for Data Analysis
• Практика с библиотекой Pandas

Packages

• Mlxtend (machine learning extensions) is a Python library of useful tools for the day-to-day data science tasks
• ML | Hydra Framework for managing configuration files, tailored for ML projects
• Lazy Predict Lazy Predict helps build a lot of basic models without much code and helps understand which model works better without any parameter tuning.
• More Itertools
• iterative-stratification
• prettygraph
• Hypothesis Documentation
• Playwright for Python — Documentation
• Polars User Guide
• Selenium Documentation
• pytest Documentation
• Документация Beautiful Soup

SQL

• How to pass data engineering SQL interviews in big tech
• PostgreSQL Documentation
• Ультимативная дорожная карта для изучения SQL и баз данных в 2023 году

Courses

• Интерактивный тренажер по SQL
• Пакет SQL курсов:
• Основы SQL
• Продвинутый SQL
• Проектирование баз данных
• PostgreSQL Tutorial for Beginners
• Оконные функции SQL
• SQL Tutorial
• The Ultimate SQL Guide
• CS50’s Introduction to Databases with SQL
• Databases: Relational Databases and SQL (Stanford Online)
• Excel to MySQL: Analytic Techniques for Business
• Intro to SQL: Querying and managing data (Khan Academy)
• Introduction to Structured Query Language (SQL)
• Learn SQL (Codecademy)
• Learn SQL Basics for Data Science
• SQL Analytics Training (Mode SQL Tutorial)
• Введение в базы данных (Stepik)
• Симулятор SQL (karpov.courses)
• Учебник по SQL (SQL Academy)

Practice

• Онлайн тренажер SQL Academy
• Ace the SQL Interview
• Practice SQL
• SQLBolt. Learn SQL with simple, interactive exercises.
• SQL Tutorial by w3schools
• PostgreSQL Exercises
• The Querynomicon. An Introduction to SQL for Wary Data Scientists
• SQL Challenges
• SQL Squid Game
• DataLemur SQL Interview Questions
• HackerRank: SQL Practice
• Practical SQL for Data Analysis
• SQL Murder Mystery
• SQL-EX.RU
• 8 Week SQL Challenge

Machine Learning

Sites

• Machine Learning Mastery by Jason Brownlee
• Машинное обучение для людей. Разбираемся простыми словами
• Анализ малых данных
• Kaggle Competitions
  • How to Win a Kaggle Competition
• The Illustrated Machine Learning
• MLU-EXPLAIN
• ML Code Challenges
• Papers With Code

Courses

• Open Machine Learning Course by Yury Kashnitsky
• Машинное обучение (курс лекций, К.В.Воронцов)
• Прикладные задачи анализа данных (курс лекций, А.Г.Дьяконов) video
• Алгоритмы Машинного обучения с нуля
• Stanford CS229: Machine Learning by Andrew Ng
• Kaggle Learn
• Google Machine Learning Courses
• End to End Machine Learning by Brandon Rohrer
• Машинное Обучение в Python: Большой Курс для Начинающих
• Обучение работе с ML‑сервисами от Yandex Cloud
• Introduction to Machine Learning (I2ML)
• MACHINE LEARNING @ VU
• Practical Machine Learning
• Machine Learning Engineer Learning Path
• Machine Learning Course Notes
• Data Science for Beginners (Microsoft)
• Data Science: Visualization (HarvardX)
• High-Dimensional Data Analysis (HarvardX PH525.4x)
• Machine Learning Crash Course
• Machine Learning for Beginners (Microsoft)
• Open ML Course: Классические модели ML (autumn 2024)
• ml-course-hse by Evgeny Sokolov
• mlcourse.ai
• qmlcourse: курс по квантовому машинному обучению
• Введение в Data Science и машинное обучение
• Машинное обучение (А.Г. Дьяконов, МГУ)
• Машинное обучение (К.В. Воронцов)

Books

• Учебник по машинному обучению от ШАД
• An Introduction to Statistical Learning by Gareth James, Daniela Witten, Trevor Hastie, Rob Tibshirani
• The Elements of Statistical Learning by Trevor Hastie, Robert Tibshirani, Jerome Friedman
• Machine Learning Simplified: A gentle introduction to supervised learning by Andrew Wolf
• The Kaggle Book
• Feature Engineering and Selection: A Practical Approach for Predictive Models by Max Kuhn and Kjell Johnson
• Clean Machine Learning Code
• Interpreting Machine Learning Models With SHAP: A Guide With Python Examples And Theory On Shapley Values
• Interpretable Machine Learning. A Guide for Making Black Box Models Explainable by Christoph Molnar
• Machine Learning Q and AI. Expand Your Machine Learning & AI Knowledge With 30 In-Depth Questions and Answers by Sebastian Raschka
• Reliable Machine Learning: Applying SRE Principles to ML in Production by Cathy Chen
• Models Demystified. A Practical Guide from Linear Regression to Deep Learning
• Machine Learning from Scratch. Derivations in Concept and Code
• Supervised Machine Learning for Science by Christoph Molnar & Timo Freiesleben
• Machine Learning Refined: Notes, Exercises, Presentations, and Sample Chapters
• Дьяконов А.Г. "Машинное обучение и анализ данных"
• Виктор Владимирович Китов. Машинное обучение
• Thinking Clearly with Data: A Guide to Quantitative Reasoning and Analysis
• Applied geospatial Data Science with Python: Leverage geospatial data analysis and modeling to find unique solutions to environmental problems
• Foundations of Machine Learning by Mohri, Rostamizadeh, Talwalkar
• Hands-On Machine Learning with Scikit-Learn, Keras and TensorFlow
• Learning Machine: An Interactive Book of Machine Learning
• Machine Learning Bookcamp
• Probabilistic Machine Learning: Advanced Topics (Kevin Murphy)
• Probabilistic Machine Learning: An Introduction (Kevin Murphy)

Cheetsheets

• Supervised Learning
• Unsupervised Learning
• Tips and Tricks
• Machine learning cheat sheet
• Machine Learning Glossary
• Cheat Sheets for Machine Learning and Data Science
• Обзор методов кластеризации (scikit-learn.ru)

Articles

• Anthology of Modern Machine Learning
• Cross-validation strategies for data with temporal, spatial, hierarchical, or phylogenetic structure
• ML Papers of The Week by DAIR.AI
• word2vec Parameter Learning Explained
• Ilya 30u30
• Introduction to Machine Learning by Laurent Younes
• A Comprehensive Benchmark of Machine and Deep Learning Across Diverse Tabular Datasets
• An Empirical Comparison of Supervised Learning Algorithms
• Better Generalization with Semantic IDs: A Case Study in Ranking for Recommendations
• CatBoost, XGBoost и выразительная способность решающих деревьев
• DeepFM: A Factorization-Machine based Neural Network for CTR Prediction
• Multi-gate Mixture-of-Experts (MMoE) — Google, KDD 2018
• Multitask Learning (Caruana, 1997)
• When to Choose CatBoost Over XGBoost or LightGBM
• Метод опорных векторов (SVM): подходы, принцип работы и реализация с нуля на Python
• Основы линейной регрессии

Applied ML

• geographic Data Science with Python
• WTTE-RNN - Less hacky churn prediction
• Прикладной анализ данных в социальных науках
• Ансамбли в машинном обучении
• Machine Learning for Imbalanced Data
• Валидация моделей машинного обучения
• Do Machine Learning Models Memorize or Generalize?
• Soccer Analytics Handbook
• lifetimes
• retentioneering-tools

Blogs

• Applying Machine Learning by Eugene Yan
• Eugene Yan
• Data Science Project Quick-Start
• Writing is Learning: How I Learned an Easier Way to Write
• Uncommon Uses of Python in Commonly Used Libraries
• Andrey Lukyanenko
• A third life of a personal pet-project for handwritten digit recognition
• A machine learning roadmap for beginners in 2026
• Dan Bader
• Matthew Brett
• Introducing principal component analysis
• Amit Chaudhary
• Andrej Karpathy
• Jay Alammar
• Lilian Weng
• Data science blogs
• Keep the gradient flowing by Fabian Pedregosa
• Irrational Exuberance by Will Larson

Feature Engineering

• Лекция по курсу ММО - 24.03.2021, Отбор признаков (Feature selection)
• Kaggle Tips for Feature Engineering and Selection | by Gilberto Titericz | Kaggle Days Meetup Madrid
• featurewiz is the best feature selection library for boosting your machine learning performance with minimal effort and maximum relevance using the famous MRMR algorithm
• Feature Ranking and Selection
• Feature Engineering A-Z
• Feature Selection in Machine Learning by Soledad Galli
• OptBinning
• feature-engine

Tutorials

• CatBoost - An In-Depth Guide
• Введение в библиотеку Transformers и платформу Hugging Face
• Build a Telegram chatbot with any AI model under the hood
• ML Primer by Boris Tseytlin
• Decision Trees. The unreasonable power of nested decision rules
• Ensemble Methods and Decision Trees
• Awesome CatBoost
• Beware Default Random Forest Importances
• Understanding Tree SHAP for Simple Models (SHAP docs)

Blog posts

• Векторное представление товаров Prod2Vec: как мы улучшили матчинг и избавились от кучи эмбеддингов
• Some characteristics of best-in-class ML portfolio projects
• Как метод подмены задачи борется с несовершенством данных (и мира)
• Feature Selection — Exhaustive Overview by Danny Butvinik
• A highly anticipated Time Series Cross-validator is finally here
• Интерпретация моделей и диагностика сдвига данных: LIME, SHAP и Shapley Flow
• Мое первое серебро на Kaggle или как стабилизировать ML модель и подпрыгнуть на 700 мест вверх
• Soccer Analytics 2022 Review
• Эй-Яй, крипта, MLOps и командный пет-проджект by yorko
• Understanding UMAP
• A new perspective on Shapley values, part I: Intro to Shapley and SHAP
• A new perspective on Shapley values, part II: The Naïve Shapley method
• 10 первых ошибок в карьере ML-инженера
• Understanding the Bias-Variance Tradeoff by Seema Singh
• The “Bias-Variance Trade-Off” Explained Practically (In Python)
• Модельный риск: как увеличить эффективность работы ML моделей в большой компании
• Эффективные ансамбли
• Reflecting on 18 years at Google
• Как не перестать быть data driven из-за data driften, или Пару слов о дрейфе данных
• В чём польза теоремы Байеса — или как управлять неопределённостью
• AI by Hand with Prof. Tom Yeh for AI Professionals
• CatBoost и LightGBM: особенности алгоритмов градиентного бустинга
• Кластеризация в ML: от теории популярных алгоритмов до реализации с нуля на Python
• Оценка качества кластеризации: свойства, метрики, код

Kaggle

• Best Kaggle Competitions for Beginners
• Roadmap for Beginners
• The Best Tutorial for Beginners
• Learning Materials on Kaggle
• Data Science for tabular data: Advanced Techniques
• Feature Selection with Null Importances
• The Most Comprehensive List of Kaggle Solutions and Ideas
• NLP:
  • Approaching (Almost) Any NLP Problem on Kaggle
  • Long Text Sentiment Classification BERT Windowing
• EDA Pipelines:
  • Titanic:
    • EDA To Prediction(DieTanic)
    • Titanic Top 4% with ensemble modeling
• Ensembling:
  • Introduction to Ensembling/Stacking in Python
• Разбор kaggle-соревнования "American Express" в MISIS AI Lab
• Tinkoff Data Science Challenge — Станислав Семёнов о кодировании категориальных признаков

Metrics

• Classification metrics (precision, recall, F1 and Matthews correlation coefficient)
• Classification metrics (precision, recall, F1 and Matthews correlation coefficient) vs Balanced Accuracy
• An Introduction to ROC Analysis (Fawcett, 2006)
• Population Stability Index
• The Meaning and Use of the Area Under a ROC Curve (Hanley & McNeil, 1982)
• The Relationship Between Precision-Recall and ROC Curves (Davis & Goadrich, 2006)
• Александр Дьяконов — конспект про метрики (ML metrics)

Datasets

• 24 Useful Open Datasets for Natural Language Processing
• Подборка источников геоданных
• Awesome Public Datasets

Assignments

• Stanford CS224n: Natural Language Processing with Deep Learning
  • Assignment 1: Introduction to word vectors
  • Assignment 2: Derivatives and implementation of word2vec algorithm
  • Assignment 3: Dependency parsing and neural network foundations
  • Assignment 4: Neural Machine Translation with sequence-to-sequence, attention, and subwords
  • Assignment 5: Self-supervised learning and fine-tuning with Transformers
• Stanford CS231n: Convolutional Neural Networks for Visual Recognition & Course notes
  • Assignment 1: Image Classification, kNN, SVM, Softmax, Fully-Connected Neural Network
  • Assignment 2: Fully-Connected Nets, Batch Normalization, Dropout, Convolutional Nets
  • Assignment 3: Image Captioning with Vanilla RNNs, LSTMs, Transformers, Network Visualization, Generative Adversarial Networks
• Stanford CS229: Machine Learning & Summer version & Assignments from Fall 2018
• Pen and Paper Exercises in Machine Learning

Other

• StatQuest with Josh Starmer
• A new perspective on Shapley values:
  • Part I: Intro to Shapley and SHAP
  • Part II: The Naïve Shapley method
• Model Evaluation, Model Selection, and Algorithm Selection in Machine Learning by Sebastian Raschka
• How to avoid machine learning pitfalls: a guide for academic researchers by Michael A. Lones
• Core Machine Learning Skills
• Discover machine learning, data science & robotics competitions
• AI and Data Scientist Roadmap
• Public: Learning Map to become a Data & AI Scientist at Careem
• Компетенции DS-инженеров в Авито
• Лекции Науки о данных (МФТИ)
• Courses at Stanford relative to AI
• A Critical Field Guide for Working with Machine Learning Datasets
• AugLy
• How HDBSCAN Works
• Yellowbrick
• auto-sklearn

MLOps

General

• FastAPI for Machine Learning: Live coding an ML web application with the creator of FastAPISebastián Ramírez
• Build your MLOps stack
• MLOps и production подход к ML исследованиям
• MLOps Guide
• MLOps guide by Chip Hyyen
• MLOps Zoomcamp
• MLOps и production подход к ML исследованиям 2.0: Видео + Курс
• THE ULTIMATE DOCKER COMPOSE CHEAT SHEET
• Practitioner's guide to MLOps by Google
• Advanced курс по MLOps: Kubernetes, Kafka, CI/CD
• Awesome MLOps
• Awesome MLOps (Tools)
• DTU MLOps Course
• Evidently
• Introduction to Machine Learning Systems (Vijay Janapa Reddi)
• Lean Data Science (LeanDS) — вводный курс
• MLOps-Basics
• Made With ML: MLOps Course
• Open-Source ML Observability Course
• Towards MLOps: Technical Capabilities of a Machine Learning Platform
• Мини-курс по MLOps (Промышленный ML)
• Управление вычислениями: средний уровень

Other

• Complete Docker Course - From BEGINNER to PRO!
• Docker Containers and Kubernetes Fundamentals
• Изучение Docker для начинающих

Deep Learning

Books

• The Little Book of Deep Learning by François Fleuret
• Deep Learning with Python by François Chollet
• Multimodal Deep Learning
• Dive into Deep Learning I prefer going through this book using Amazon SageMaker
• Understanding Deep Learning by Simon J.D. Prince
• Deep Learning by Ian Goodfellow, Yoshua Bengio and Aaron Courville
• Deep Learning for Coders with Fastai and PyTorch: AI Applications Without a PhD by Jeremy Howard and Sylvain Gugger
• Deep Learning. Foundations and Concepts by Chris Bishop and Hugh Bishop
• Mastering PyTorch by Ashish Ranjan Jha
• The Tensor Cookbook by Thomas Dybdahl Ahle
• Deep Learning and Computational Physics
• Mathematical Introduction to Deep Learning: Methods, Implementations, and Theory by Arnulf Jentzen, Benno Kuckuck and Philippe von Wurstemberger
• Виктор Владимирович Китов. Глубокое обучение
• Grokking Deep Learning — code repository

Courses

• Deep Learning Specialization
• MIT 6.S191 Introduction to Deep Learning
• Full Stack Deep Learning - Course 2022
• 11-785 Introduction to Deep Learning from Carnegie Mellon University
• Neuromatch Academy: Deep Learning
• Efficient Deep Learning Systems by Yandex School of Data Analysis
• Short Courses by DeepLearning.AI
• TinyML and Efficient Deep Learning Computing
• Practical Deep Learning
• Practical Deep Learning for Coders part 2: Deep Learning Foundations to Stable Diffusion
• PyTorch for Deep Learning & Machine Learning (video) + Learn PyTorch for Deep Learning: Zero to Mastery book (site)
• Deep Learning Fundamentals by Sebastian Raschka and Lightning AI
• Future of AI is Foundation Models & Self-Supervised Learning
• Artificial Intelligence for Beginners
• 11-785 Introduction to Deep Learning + 11785 Spring 2024 Lectures
• Stanford CS 230 ― Deep Learning
• Convolutional Neural Networks
• Recurrent Neural Networks
• Deep Learning Tips and Tricks
• CS 330: Deep Multi-Task and Meta Learning
• Deep Learning with Catalyst
• Practical DL
• Deep Learning from the Foundations by fast.ai
• PyTorch Tutorials - Complete Beginner Course
• Школа глубокого обучения
• Neural Networks: Zero to Hero by Andrej Karpathy
• CUDA Mode: Lectures + Video
• Deep Learning IP-Paris
• CS565600 Deep Learning. Fundamentals of machine learning, deep learning, and AI
• Introduction to Deep Learning (I2DL) (IN2346)
• CS 886: Recent Advances on Foundation Models
• DEEP LEARNING COURSE
• CS236 Deep Generative Models
• 10-202: Introduction to Modern AI
• Deep Learning in Finance (Stepik)
• Hugging Face Audio Course

Tutorials

• Introduction to Deep Learning by Sebastian Raschka
• Коллекция ручных задачек о нейросетях
• A collection of various deep learning architectures, models, and tips for TensorFlow and PyTorch in Jupyter Notebooks by Sebastian Raschka
• Deep Learning Tuning Playbook by Google
• A Step by Step Backpropagation Example
• PyTorch Fundamentals by Microsoft
• labml.ai Annotated PyTorch Paper Implementations
• Grokking PyTorch
• The Incredible PyTorch
• AI Fundamentals. Concepts, Definitions, Terms
• A Guide to Production Level Deep Learning
• A Gentle Introduction to torch.autograd
• Introduction to deep learning
• PyTorch internals
• A Recipe for Training Neural Networks (Andrej Karpathy)
• Machine Learning Collection (Aladdin Persson)
• Neural Networks (MLU-Explain)

Blogs & Blog posts

• WHAT IS TORCH.NN REALLY? by Jeremy Howard, fast.ai
• О «раздутом пузыре» нейросетей
• Cтатьи от команды DeepSchool
• Полезные материалы про PyTorch
• AstraBlog
• Deep Neural Nets: 33 years ago and 33 years from now (Andrej Karpathy)
• How to Train Really Large Models on Many GPUs? (Lilian Weng)
• Jia-Bin Huang — YouTube Channel

Other

• Deep Learning Interviews: Hundreds of fully solved job interview questions from a wide range of key topics in AI
• A Cookbook of Self-Supervised Learning
• Adam: A Method for Stochastic Optimization
• Backpropagation Applied to Handwritten Zip Code Recognition (LeCun et al., 1989)
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Dropout: A Simple Way to Prevent Neural Networks from Overfitting
• Generative Adversarial Nets
• Highly Accurate Protein Structure Prediction with AlphaFold

Generative AI

• Generative AI for Beginners
• A Comprehensive Survey of AI-Generated Content (AIGC)
• Generative AI with Large Language Models (Coursera)
• Hugging Face Diffusion Models Course

NLP

Books

• Natural Language Processing with Transformers by Lewis Tunstall, Leandro von Werra adn Thomas Wolf
• Speech and Language Processing by Dan Jurafsky and James H. Martin
• Transformers for Natural Language Processing by Denis Rothman

Courses

• Нейронные сети и обработка текста
• Stanford CS224N: NLP with Deep Learning + Videos + Notes
• NLP Course | For You by Lena Voita + YSDA Natural Language Processing course
• Hugging Face course
• Natural Language Processing course by Valentin Malykh
• Stanford LSA 311: Computational Lexical Semantics by Dan Jurafsky
• Stanford CS224U: Natural Language Understanding
• Введение в обработку естественного языка
• Stanford CS 224V Conversational Virtual Assistants with Deep Learning
• CS11-711 Advanced Natural Language Processing (at Carnegie Mellon University's Language Technology Institute) + Video + Assignments
• Linguistics for Language Technology
• Advanced Topics in Multimodal Machine Learning (CMU 11-877)
• Deep Learning for Natural Language Processing (DL4NLP, UvA)
• DeepNLP Course (Dan Anastasyev)
• Machine Learning University: Accelerated Natural Language Processing (AWS)
• Multilingual NLP (CMU 11-737)
• Stanford CS25: Transformers United

General

• Recommendations for Getting Started with NLP by Elvis
• Чат по NLP
• awesome-nlp. A curated list of resources dedicated to Natural Language Processing
• NLP Cheatsheet: Master NLP
• Hugging Face Tasks

Large Language Models (LLMs) / Transformers

• Stanford Webinar - GPT-3 & Beyond
• Transformer Recipe by Elvis Saravia
• Transformer, explained in detail by Igor Kotenkov
• The Practical Guides for Large Language Models
• State of GPT by Andrej Karpathy
• LLM University by Cohere
• CS324 - Large Language Models
• Generative AI exists because of the transformer. This is how it writes
• Training & Fine-Tuning LLMs for Production
• LLMOps: Building Real-World Applications With Large Language Models
• A Survey of Large Language Models
• Transformers Tutorials
• Ruformers/Руформеры
• Схема энкодера архитектуры Трансформер
• Large Language Model Course
• Insights from Finetuning LLMs with Low-Rank Adaptation by Sebastian Raschka
• LLM Bootcamp - Spring 2023
• ChatGPT Course – Use The OpenAI API to Code 5 Projects
• Self-Attention & Transformers (CS 224n: Natural Language Processing with Deep Learning)
• Build a Large Language Model (From Scratch) by Sebastian Raschka
• Hands-on LLMs Course
• LLaMA-Factory. Easy-to-use LLM fine-tuning framework (LLaMA, BLOOM, Mistral, Baichuan, Qwen, ChatGLM)
• Open LLMs. A list of open LLMs available for commercial use
• Overview of Large Language Models
• Mastering RAG: How To Architect An Enterprise RAG System
• Исчерпывающий гайд по опенсорсным языковым моделям
• Open-Source AI Cookbook
• Building LLM applications for production
• LLM Visualization
• The Illustrated Transformer by Jay Alammar
• The Annotated Transformer + Neural networks by 3Blue1Brown
• Elicit Machine Learning Reading List
• LLM Zoomcamp
• llama3 implemented from scratch
• LLM Twin Course: Building Your Production-Ready AI Replica
• Educational resources on LLMs
• A Visual Guide to Quantization. Demystifying the Compression of Large Language Models
• Super Study Guide: Transformers & Large Language Models
• Advanced RAG Techniques: Elevating Your Retrieval-Augmented Generation Systems
• CUDA-Free Inference for LLMs
• Изучаю LLM by Evgenii Nikitin
• What is the Role of Small Models in the LLM Era: A Survey
• Building LLMs from the Ground Up: A 3-hour Coding Workshop
• AI Prompt Engineering: A Deep Dive
• LLM Resources Hub
• 🤗 AI Agents Course by Hugging Face
• LLM Engineering Essentials
• Hugging Face Reasoning Course
• CS336: Language Modeling from Scratch + Video
• A Comprehensive Overview of Large Language Models
• A Survey of Transformers
• AI Alignment: A Comprehensive Survey
• Are Emergent Abilities of Large Language Models a Mirage?
• BERT (Google Research)
• BERT, ELMO и Ко в картинках
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
• Claude with the Anthropic API (Anthropic Academy)
• Compressing Large-Scale Transformer-Based Models: A Case Study on BERT
• DeepSchool: Large Language Models (course)
• DeepTutor
• GPT-4 Technical Report
• Generating Text from Language Models (ACL 2023 Tutorial)
• Learn About Transformers: A Recipe
• Llama 2: Open Foundation and Fine-Tuned Chat Models
• Patterns for Building LLM-based Systems & Products (Eugene Yan)
• Pretrained Language Model (Huawei Noah's Ark Lab)
• QLoRA: Efficient Finetuning of Quantized LLMs
• Recent Advances in Language Model Fine-tuning (Sebastian Ruder)
• RoBERTa: A Robustly Optimized BERT Pretraining Approach
• The Illustrated Retrieval Transformer (Jay Alammar)
• Yao Fu's Blog
• gpt-fast

Embeddings

• Новый взгляд на оценку русскоязычных моделей: обновлённый бенчмарк ruMTEB и лидерборд
• What are embeddings by Vicki Boykis
• Learn to Love Working with Vector Embeddings by Pinecone
• The 1950-2024 Text Embeddings Evolution Poster
• Chroma
• Milvus
• Qdrant
• ScaNN
• Vector Databases: from Embeddings to Applications (DeepLearning.AI)
• hnswlib

Reading papers with AI

• Explainpaper
• ChatPDGF
• Reimagine Research
• Discover scientific knowledge and stay connected to the world of science
• Get scientific answers by asking millions of research papers
• Otio

Prompt Engineering

• Prompt Engineering Guide + Prompt Engineering Guide
• Prompt injection with Gandalf
• Prompt Engineering
• Prompt Engineering Guide
• Awesome ChatGPT Prompts
• Advanced Prompt Engineering
• Prompt engineering Guide by Open.ai
• Prompt Of The Year: 2023
• Anthropic's Prompt Engineering Interactive Tutorial
• The Prompt Report: A Systematic Survey of Prompting Techniques
• Prompt Engineering Guide by Antrophic
• Claude 101
• AI Coding Playbook
• ChatGPT Prompt Engineering for Developers (DeepLearning.AI)
• Claude 101 (Anthropic Academy)
• Guidance (Microsoft)
• OpenPrompt
• Prompt Engineering 101: Introduction and Resources (Xavier Amatriain)
• Prompt Engineering vs. Blind Prompting (Mitchell Hashimoto)
• PromptSource
• Vibe-coding: программирование с ИИ без глубоких знаний кода (Stepik)

Tutorials

• Train and Fine-Tune Sentence Transformers Models
• Working With Text Data using Sklearn + Text feature extraction using Sklearn
• minbpe. Minimal, clean code for the (byte-level) Byte Pair Encoding (BPE) algorithm commonly used in LLM tokenization
• Text Classification Guide (Google Machine Learning Guides)
• nlp-tutorial

Blog posts

• Мультиклассификация экстремально коротких текстов классическими методами машинного обучения
• Рейтинг русскоязычных энкодеров предложений
• Как определять пользовательские намерения, о которых мы узнали 5 минут назад
• Самая большая BERT-подобная модель на русском, которая поместится на ваш компьютер
• ChatGPT как инструмент для поиска: решаем основную проблему
• GPT in 60 Lines of NumPy
• What Is ChatGPT Doing … and Why Does It Work?
• From GPT-3 to ChatGPT: Training Language Models on Instructions and Human Feedback
• Кто такие LLM-агенты и что они умеют?
• Maxime Labonne's Blog

Articles

• Word2Vec, Mikolov et al., Efficient Estimation of Word Representations in Vector Space
• FastText, Bojanowski et al., Enriching Word Vectors with Subword Information
• Attention, Bahdanau et al., Neural Machine Translation by Jointly Learning to Align and Translate
• Transformers, Vaswani et al., Attention Is All You Need
• BERT, Devlin et al., BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
• GPT-2, Radford et al., Language Models are Unsupervised Multitask Learners
• GPT-3, Brown et al, Language Models are Few-Shot Learners
• LaBSE, Feng et al., Language-agnostic BERT Sentence Embedding
• CLIP, Radford et al., Learning Transferable Visual Models From Natural Language Supervision
• RoPE, Su et al., RoFormer: Enhanced Transformer with Rotary Position Embedding
• LoRA, Hu et al., LoRA: Low-Rank Adaptation of Large Language Models
• InstructGPT, Ouyang et al., Training language models to follow instructions with human feedback
• Scaling laws, Hoffmann et al., Training Compute-Optimal Large Language Models
• FlashAttention, Dao et al., FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
• NLLB, NLLB team, No Language Left Behind: Scaling Human-Centered Machine Translation
• Q8, Dettmers et al., LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale
• Self-instruct, Wang et al., Self-Instruct: Aligning Language Models with Self-Generated Instructions
• Alpaca, Taori et al., Alpaca: A Strong, Replicable Instruction-Following Model
• LLaMA, Touvron, et al., LLaMA: Open and Efficient Foundation Language Models
• 100 Must-Read NLP Papers
• Search: Query Matching via Lexical, Graph, and Embedding Methods (Eugene Yan)

Packages

• Turbo-Alignment
  Turbo-Alignment is a library designed to streamline the fine-tuning and alignment of large language models, leveraging advanced techniques to enhance efficiency and scalability
• LitGPT
  Every LLM is implemented from scratch with no abstractions and full control, making them blazing fast, minimal, and performant at enterprise scale.
• MinT: Minimal Transformer Library and Tutorials
• Проект Natasha. Набор качественных открытых инструментов для обработки естественного русского языка (NLP)
• russian Texts Statistics
• TextDescriptives A Python library for calculating a large variety of metrics from text(s) using spaCy v.3 pipeline components and extensions.
• LangChain Documentation
• Language Interpretability Tool (LIT)
• LlamaIndex Documentation
• NL-Augmenter
• ScrapeGraphAI
• TextBox 2.0
• nlpaug

Computer Vision

• Нейронные сети и компьютерное зрение
• CS231n: Deep Learning for Computer Vision + Videos
• EECS 442: Computer Vision + Videos
• Foundations of Computer Vision by Antonio Torralba, Phillip Isola and William T. Freeman
• ImageNet Classification with Deep Convolutional Neural Networks (AlexNet)
• NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis
• Segment Anything

Graphs

• CS224W: Machine Learning with Graphs + Video
• Graph Neural Networks for RecSys
• Graph Neural Networks
• A Gentle Introduction to Graph Neural Networks (Distill)
• An Introduction to Graph Theory by Darij Grinberg
• Graph Attention Networks
• Understanding Convolutions on Graphs (Distill)
• Курс по графам знаний (KG Course 2021, ODS.ai)

Reinforcement Learning

• Spinning Up in Deep RL
• 🤗 Deep Reinforcement Learning Course
• Practical RL
• A (Long) Peek into Reinforcement Learning
• CMU 10-703: Deep Reinforcement Learning and Control
• CS 294: Deep Reinforcement Learning (UC Berkeley)
• Deep RL Bootcamp (UC Berkeley)
• DeepMind x UCL Reinforcement Learning Lecture Series
• Hugging Face Deep RL Course
• Kevin Murphy — Reinforcement Learning: An Overview
• Playing Atari with Deep Reinforcement Learning
• Policy Gradient Algorithms
• Proximal Policy Optimization Algorithms
• Reinforcement Learning Virtual School (RLVS 2021)
• Reinforcement Learning: An Introduction
• Spinning Up in Deep RL Workshop (OpenAI)
• Stable-Baselines3 Documentation
• Stanford CS234: Reinforcement Learning
• The Multi-Armed Bandit Problem and Its Solutions

RecSys

Courses

• Your first recsys by MTS
• Your Second RecSys by MTS
• Рекомендательные системы
• Deep RecSys Course by Kirill Khrylchenko
• RecSys Fall 2023 (girafe-ai)

Books

• К. Фальк. Рекомендательные системы на практике / Practical Recommender Systems by Kim Falk
• Personalized Machine Learning
• Learning to Rank for Information Retrieval and Natural Language Processing

Other

• Авито. Рекомендации
• Recommenders. Best Practices on Recommendation Systems
• Рекомендательные системы
• Рекомендательные системы: идеи, подходы, задачи
• A Survey of Deep Reinforcement Learning in Recommender Systems
• Advances and Challenges in Conversational Recommender Systems: A Survey
• Blueprints for Recommender System Architectures: 10th Anniversary Edition
• Graph Neural Networks in Recommender Systems: A Survey
• OneRec: Unifying Retrieve and Rank with Generative Recommender
• Pointwise vs Pairwise vs Listwise Learning to Rank
• Recommender Systems in Python 101
• Ultimate RecSys List
• Дропаем ранжирующие метрики в рекомендательной системе, часть 2: двухэтапные модели
• Дропаем ранжирующие метрики в рекомендательной системе: визуальный анализ и popularity bias

Packages

• Revisiting BPR

Time Series

• Временные ряды
• Topic 9. Time Series Analysis with Python
• Прогнозирование временных рядов
• Time Series
• Forecasting time series with gradient boosting: Skforecast, XGBoost, LightGBM, Scikit-learn and CatBoost by Joaquín Amat Rodrigo, Javier Escobar Ortiz
• ARIMA and SARIMAX models with Python by Joaquín Amat Rodrigo, Javier Escobar Ortiz
• Груздев А.В., Рафферти Г. Прогнозирование временных рядов с помощью Prophet, sktime, ETNA и Greykite
• Forecasting: Principles and Practice (3rd ed)
• Dive into Time-Series Anomaly Detection: A Decade Review
• M5 Forecasting - Uncertainty
• Predict Future Sales
• StatsForecast Documentation
• Time Series Analysis in Python – A Comprehensive Guide with Examples
• Time Series Forecasting With Python (Mini-Course)
• Дмитрий Макаров — вводный курс по временным рядам

Big Data

Books

• Перрен Ж.Ж. Spark в действии / Spark in Action by Jean-Georges Perrin
• Learning Spark
• Data Analysis with Python and PySpark
• POSTGRES: Первое знакомство
• Высоконагруженные приложения — Martin Kleppmann

Other

• Анализируем данные с помощью фреймворка Spark
• PySpark для аналитика. Как правильно просить ресурсы и как понять, сколько нужно брать
• PySpark для аналитика. Как выгружать данные с помощью toPandas и его альтернатив
• Spark Architecture by FaangTalk
• SPARK для «малышей»
• Apache Superset Documentation
• ClickHouse Documentation (русская версия)
• Cumulative Table Design
• Hadoop. Система для обработки больших объемов данных (Stepik)
• Palantir PySpark Style Guide
• PySpark Style Guide (MrPowers)

System Design

• The System Design Primer
• Algorithms you should know before you take system design interviews
• Top 14 System Design interview questions for software engineers
• System Design for Interviews and Beyond
• System Design
• System Design by Karan Pratap Singh
• System Design 101
• Systems Design Interview Guide
• Designing Distributed Systems
• System Design Interview – Step By Step Guide
• Designing Data-Intensive Applications and its related books
• A Senior Engineer's Guide to the System Design Interview
• Intro to System Design
• System Design Newsletter
• Awesome System Design
• Design Docs at Google
• System Design Fight Club
• What happens when you type google.com into your browser's address box and press enter?
• ByteByteGo
• Coding Interviews Blog Archive
• Distributed Systems
• Grokking Modern System Design Interview for Engineers & Managers
• Grokking the System Design Interview
• System Design. Подготовка к сложному интервью
• codeKarle
• «Возьмите инициативу на себя»: готовимся к System Design Interview
• Всё, что нужно знать о System Design

Machine Learning System Design

• Stanford CS 329S: Machine Learning Systems Design
• ML System Design
• Шаблон ML System Design Doc от телеграм-канала Reliable ML ML System Design - ML System Design Doc. Лекция-бонус от Reliable ML
• Machine learning design primer by Ibragim Badertdinov
• How to Write Design Docs for Machine Learning Systems -> ml-design-doc
• Что я бы хотел знать про ML System Design раньше
• Почему анализ ошибок – это начало разработки ML системы, а не конец?
• ML Systems Design Interview Guide
• Machine Learning System Design by Valerii Babushkin and Arseny Kravchenko
• Designing Machine Learning Systems by Chip Huyen
• Machine Learning Engineering Online Book
• ML system design: 500 case studies to learn from
• Machine Learning System Design Interview by Ali Aminian, Alex Xu + Solutions
• The 9-Step ML System Design Formula
• CSCE 585 Machine Learning Systems: Lectures + Video
• Machine Learning in Production: From Models to Products
• ML System Design by Machine Learning REPA
• ML for Developers
• Machine Learning System Design Doc Examples
• Machine Learning in Production by Carnegie Mellon University
• Crack ML System Design Interviews Like a Pro
• Grokking the Machine Learning Interview
• Machine Learning System Design (Educative)
• Machine Learning Systems Design: Case Studies
• Stanford MLSys Seminars
• System Design for Recommendations and Search

Math

General

• В Data Science не нужна математика (Почти)
• Mathematics Of Machine Learning | MIT
• How to beat maths anxiety
• Engineering Math: Differential Equations and Dynamical Systems
• Mathematics for Machine Learning
• The Complete Mathematics of Neural Networks and Deep Learning
• Математика для анализа данных
• Pen and Paper Exercises in Machine Learning by Michael Gutmann
• Highlights of Calculus (MIT OpenCourseWare)
• Mathematics for Machine Learning Specialization (Imperial College London)
• Mathematics for Machine Learning and Data Science Specialization (DeepLearning.AI)
• Математический анализ — лекции А.А. Никитина
• Математический анализ. Теория функций одной переменной (МГУ)

Linear Algebra

• Introduction to Linear Algebra by Gilbert Strang
• The Matrix Calculus You Need For Deep Learning
• Linear Algebra for Data Science
• immersive linear algebra by J. Ström, K. Åström, and T. Akenine-Möller
• Linear Algebra Review and Reference by Zico Kolter
• Linear Algebra for Data Science
• Engineering Math: Vector Calculus and Partial Differential Equations
• Engineering Math: Crash Course in Complex Analysis
• Essence of Linear Algebra (3Blue1Brown)
• Introduction to Linear Models and Matrix Algebra (Harvard PH525.2x)
• Matrix Methods in Data Analysis, Signal Processing, and Machine Learning (MIT 18.065)

Probability and Statistics

• Основы статистики + Основы статистики. Часть 2 + Основы статистики. Часть 3
• Statistics and probability from Khan Academy
• CS109: Probability for Computer Scientists + Course Book + Video
• Математическая статистика и AB-тестирование
• 12 бесплатных материалов по статистике – разберется каждый
• Математическая статистика. Начало
• Z Statistics by Justin Zeltzer
• The Beginner's Guide to Statistical Analysis by Scribbr
• Прикладная статистика. Репозиторий для линейки онлайн-курсов по статистике
• Yet another matstat 2026 (Филипп Ульянкин)
• Multivariate statistics
• R2D3 is an experiment in expressing statistical thinking with interactive design
• Statistical Rethinking
• Bayesian Statistics the Fun Way: Understanding Statistics and Probability with Star Wars, LEGO, and Rubber Ducks by Will Kurt
• Seeing theory. A visual introduction to probability and statistics
• The Book of Statistical Proofs
• Lessons in Statistical Thinking by Daniel Kaplan
• Прикладная статистика
• Statistics For Applications + Video
• Вся основная теория по A/B-экспериментам
• Statistics 110: Probability
• Introduction to Statistical Learning using Python
• Economertrics Notes by Peter Hull
• The Cartoon Guide to Statistics
• Probability Bootcamp
• A Short Note on P-Value Hacking by Nassim Nicholas Taleb
• Brandon Foltz
• Econometrics (Bruce E. Hansen)
• Fifty Challenging Problems in Probability with Solutions (Mosteller)
• Intro to Statistics (Udacity)
• Probability and Statistics for Economists (Bruce E. Hansen)
• StatQuest with Josh Starmer — Video Index
• Statistics (Full Length Videos) — Professor Leonard
• Statistics 101 (Cognitive Class)
• What Teachers Should Know about the Bootstrap: Resampling in the Undergraduate Statistics Curriculum
• [МФТИ, 2021] Прикладная статистика
• zedstatistics
• А/Б тестирование: множественная проверка гипотез
• Вероятность и статистика с Глебом Михайловым
• Голая статистика (Чарльз Уилан)
• Математическая статистика (Stepik)
• Математическая статистика — лектор И.В. Родионов (осень 2019)
• Основы статистики (Яндекс Практикум)
• Теория вероятностей (Stepik)
• Эконометрика (НИУ ВШЭ, Борис Демешев)

Causal Inference

• Causal Inference: What If
• Causal Inference and Its Applications in Online Industry
• Applied Causal Inference Powered by ML and AI
• A Survey on Causal Inference
• Brady Neal — Which Causal Inference Book?
• Causal Inference & Econometrics Reading List by Anna Stavniychuk
• Causal Inference: The Mixtape — Python Notebooks
• CausalML
• CausalNex
• DoWhy
• did: Difference-in-Differences (R package)

A/B Tests

Courses

• A/B TESTING
• Курс по Прикладной статистике от Академии Аналитиков Авито
• A/B Testing & Experimentation Roadmap
• А/Б-тестирование (Филипп Ульянкин)
• Теория и практика онлайн-экспериментов (ВШЭ)
• Теория и практика онлайн-экспериментов (ВШЭ, Нерсес Багиян)

General

• Trustworthy Online Controlled Experiments by Ron Kohavi
• Подборка ссылок по A/B тестированию от Валеры Бабушкина
• Most cited sources in A/B Testing by Ron Kohavi
• A/B Testing RoadMap
• Чеклист А/Б эксперимента + Шаблон проведения А/Б эксперимента
• Practitioner’s Guide to Statistical Tests by VK Team
• Statistical Challenges in Online Controlled Experiments: A Review of A/B Testing Methodology
• stattests: код к Practitioner's Guide to Statistical Tests
• Методичка по AB-тестированию от аналитиков Авито

Blog posts

• Шесть причин, почему ваши A/B-тесты не работают
• АБ-тесты — это не только ценный мех… Но еще и процессы
• Стратификация. Как разбиение выборки повышает чувствительность A/B теста
• 50 оттенков линейной регрессии, или почему всё, что вы знаете об A/B тестах, помещается в одно уравнение
• Выбросы в A/B тестах: проблемы при дизайне, подведении итогов и автоматизации

Metrics

• Продуктовому аналитику: 7 методик, чтобы находить кратные точки роста продукта
• Unit-экономика за 45 минут (LTV/CAC, MRR, ARPU, NPS...)
• Improving the Sensitivity of Online Controlled Experiments by Utilizing Pre-Experiment Data (CUPED)
• Measuring Metrics

Lists of Materials

• NLP Pandect
• Start Career in DS: навигация по постам
• Extra materials for ml-mipt course
• Awesome FastAPI
• Curated papers, articles, and blogs on data science & machine learning in production
• The Breaking Into Data Handbook
• Machine Learning Tutorials
• Learn-Data-Science-For-Free
• Data-Science-EBooks
• A list of resources for learning ML
• Machine Learning Resources
• Machine Learning Roadmap 2020
• Подборка ресурсов по машинному обучению (demidovakatya)
• Путь к познанию мистерий обучения машин без траты денежных ресурсов

Other

• Interactive Tools for Machine Learning, Deep Learning, and Math
• Ilya Sutskever’s Reading List
• Robotics Course by Hugging Face
• Machine Learning for Fluid Dynamics
• Maths, CS & AI Compendium

Adjacent

Material merged from the data_science_resources repo: adjacent to Data Science rather than part of it.

Computer Science

Papers

• Papers We Love

General

• Open Source Society University
• Harvard CS50 + Video
• Четыре половины успеха инженера
• Матожидание количества успешных гипотез
• Document-driven management. Почему писать документы — это круто
• 30 Seconds of Code
• An overview of HTTP (MDN)
• Free Programming Books
• How to Develop Perfect CRUD: Good Practices for Developing Back-End Apps
• Stanford: The Modern Software Developer — Assignments
• You Don't Know JS (русский перевод)
• Курс по документированию REST API
• Курс про лицензии и Open Source (ODS.ai)

Code Review

• How Google takes the pain out of code reviews, with 97% dev satisfaction
• How to do a code review + conventional: comments. Comments that are easy to grok and grep
• The CL author’s guide to getting through code review
• The Code Review Pyramid

Git

• Изучаем ветвление в git
• Git Tips and Tricks for Effective Developers
• Step-by-step guide to contributing on GitHub
• Oh Shit, Git!?!
• Git для начинающих (Слёрм)
• Introduction to GitHub (GitHub Skills)
• Введение в Git (Хекслет)
• Курс по Git (Илья Кантор)

Linux

• Linux commands
• The Art of Command Line
• Командная строка для разработчиков – cli-for-dev
• Bash Scripting Tutorial for Beginners

Tutorials

• The Linux command line for beginners

Tech Lead / Team Lead / Staff

• Everything on team leadership
• Team Lead Simulator
• Teamlead Roadmap
• Staff archetypes
• The Mochary Method Curriculum
• The SPACE of Developer Productivity

Books

Nonfiction

• Atomic Habits
• 9 Books I Read In 2022 That Already Reshaped My Life
• Reading List by Lex Fridman
• Crucial Conversations Tools for Talking When Stakes Are High, Second Edition
• Drive: The Surprising Truth About What Motivates Us — Daniel Pink
• Вы, конечно, шутите, мистер Фейнман! — Ричард Фейнман

Writing

• On Writing Well: The Classic Guide to Writing Nonfiction

Note-taking system

Anki

• How to Remember Anything. A study technique for all ages and all subjects
• Algo Deck
• Spaced Repetition Systems Have Gotten Way Better
• The Janki Method

Zettelkasten

• The FUN and EFFICIENT note-taking system I use in my PhD
• Stop Taking Regular Notes; Use a Zettelkasten Instead
• Где и как хранить свои знания: концепция «внешнего мозга»
• Zettelkasten.de Blog

Newsletters

Data Science

• Data Science Simplified
• Beyond Data by Adam Sroka

Preparing for Interviews

• Nick Singh's Tech & Careers Newsletter
• Newsletter by Emma Ding
• The MLnotes Newsletter

NLP

• NLP Newsletter

Machine Learning & Deep Learning

• MACHINE LEARNING QUESTIONS
• Mindful Modeler by Christoph Molnar
• Tuesday Musings by Radek Osmulski
• The Batch. What Matters in AI Right Now
• Newsletter by Eugene Yan
• Boris Again
• Ahead of AI by Sebastian Raschka
• Underfitted by Santiago Valdarrama

Productivity

• The 3-2-1 Newsletter

Software Engineering

• The Pragmatic Engineer by Gergely Orosz

System Design

• ByteByteGo Newsletter

Career & Self-development

• Путь Лемминга. Про планирование карьеры, выгорание, здоровье, конкуренцию и т.п.
• Публичные выступления
• 5 Mindset Strategies For Success And Prosperity
• Hamming, "You and Your Research"
• The Feynman Lectures on Physics
• You don’t need to work on hard problems
• How To Be Successful by Sam Altman
• What I Wish Someone Had Told Me
• 95%-ile isn't that good
• Etsy Engineering Career Ladder
• How to Pick a Career (That Actually Fits You)
• Learning How to Learn (Coursera)
• Методичка по поиску работы в ML/DS и IT

Productivity

• Reminder — это медиа о здоровье, саморазвитии и практической философии
• How to Make Learning as Addictive as Social Media | Luis Von Ahn | TED
• Тебе нужна своя стратегия
• YearCompass

Finance

• How to Get Rich
• ​Инвестиционные принципы Чарли Мангера
• If You Can: How Millennials Can Get Rich Slowly — William Bernstein

Reading

• Bionic Reading

Website Development

• Crafting My Personal Website: Jekyll, GitHub Pages, and a Custom Domain