ML - gusenov/kb GitHub Wiki
- HEP Software Foundation Training Material
- Stepik
- Курс по машинному обучению от Mail.Ru Group
- OpenAI
- Википедия
- Илон Маск и Сэм Альтман (президент венчурного фонда Y Combinator) запустили OpenAI в конце 2015.
- GitHub
- OpenAI Codex
- Википедия
- Hugging Face – The AI community building the future.
- Хендбуки Академии Яндекса / Учебник по машинному обучению
- Neural networks and deep learning by Michael Nielsen
- PapersWithCode.com
- What’s Really Going On in Machine Learning? Some Minimal Models by Stephen Wolfram
- Хабр / Red Hat выпустила дистрибутив Red Hat Enterprise Linux AI для задач машинного обучения
- Gradio is the fastest way to demo your machine learning model with a friendly web interface so that anyone can use it, anywhere!
- gradio-app/gradio Build and share delightful machine learning apps, all in Python.
- MIT / “Periodic table of machine learning” could fuel AI discovery shows how more than 20 classical algorithms are connected. The new framework sheds light on how scientists could fuse strategies from different methods to improve existing AI models or create new
- SecurityLab.ru / Таблица Менделеева для нейросетей: MIT разложил ИИ по полочкам
- ONNX.ai is an open format built to represent machine learning models. ONNX defines a common set of operators - the building blocks of machine learning and deep learning models - and a common file format to enable AI developers to use models with a variety of frameworks, tools, runtimes, and compilers.
- onnx/onnx Open standard for machine learning interoperability
- cookiengineer/machine-learning-for-dummies Machine Learning for Dummies (aka Artificial Intelligence aka Deep Learning)
- HuggingFace.com / Learn / Diffusion Models Course
GitHub
- How to write a neural network completely from scratch in C++ in a weekend
- dair-ai/ML-Course-Notes: Lecture notes on all topics related to machine learning, NLP, and AI.`
- chiphuyen/machine-learning-systems-design: A booklet on machine learning systems design with exercises. NOT the repo for the book "Designing Machine Learning Systems"
Wikipedia
- Template:Differentiable computing
- Differentiable programming
- TensorFlow (Google)
- PyTorch (Facebook)
- One-shot learning
- Multimodal learning
- Foundation models is a large artificial intelligence model trained on a vast quantity of unlabeled data at scale (usually by self-supervised learning) resulting in a model that can be adapted to a wide range of downstream tasks.
- Reinforcement learning is an area of machine learning concerned with how intelligent agents ought to take actions in an environment in order to maximize the notion of cumulative reward.
- Synthetic data is information that's artificially generated rather than produced by real-world events.
- Neural scaling law is a scaling law relating parameters of a family of neural networks.
Math
- freeCodeCamp.org
- MATH FOR DEEP LEARNING. What You Need to Know to Understand Neural Networks by Ronald T. Kneusel - 344 p.
- Algebra, Topology, Differential Calculus, and Optimization Theory For Computer Science and Machine Learning by Jean Gallier and Jocelyn Quaintance, Department of Computer and Information Science, University of Pennsylvania
TensorFlow
- Neural Nets & Tensor Flow by Peter Kriens
- Beginning Machine Learning in the Browser. Quick-start Guide to Gait Analysis with JavaScript and TensorFlow.js by Nagender Kumar Suryadevara - 182 pages
- Convolutional Neural Networks with Swift for Tensorflow. Image Recognition and Dataset Categorization by Brett Koonce - 245 pages
- A free 7-hour course on TensorFlow 2.0
Cloud
- Practical Machine Learning with AWS. Process, Build, Deploy, and Productionize Your Models Using AWS by Himanshu Singh - 241 pages
Q&A
Коллекции
- vc.ru / Machine learning
- https://vk.com/machine_learning_and_data_mining
- https://vk.com/neural_network_society
- https://vk.com/analysis_of_data
- https://vk.com/intelligent_agents
Books
- Programming Collective Intelligence by Toby Segaran - 362 pages
- Machine Learning for Streaming Data with Python: Rapidly build practical online machine learning solutions using River and other top key frameworks by Joos Korstanje - 258 pages
- Practical Simulations for Machine Learning. Using Synthetic Data for AI by Paris and Mars Buttfield-Addison, Tim Nugent, and Jon Manning - 331 pages
- "Pattern Recognition and Machine Learning" by @ChrisBishopMSFT
- The Shape of Data. Geometry-Based Machine Learning and Data Analysis in R by Colleen M. Farrelly and Yaé Ulrich Gaba - 264 pages
- Encyclopedia of Machine Learning - 1031 pages
Deep Learning
- Dive into Deep Learning (book) provide a good balance of theory and hands-on code examples
- Introduction to Deep Learning
- NVIDIA
- NVIDIA Deep Learning Institute
- NVIDIA On-Demand Explore the extensive catalog of sessions, podcasts, demos, research posters and more.
- NVIDIA/DeepLearningExamples State-of-the-Art Deep Learning scripts organized by models - easy to train and deploy with reproducible accuracy and performance on enterprise-grade infrastructure.
- 3D Deep Learning with Python by Xudong Ma , Vishakh Hegde , Lilit Yolyan - 236 pages
- Python Deep Learning Tutorial
- Stepik / Школа глубокого обучения МФТИ
- O’Reilly / Build a super fast deep learning machine for under $1,000
- HuggingFace.com / Learn / Deep Reinforcement Learning Course
Transformers
- Wikipedia
- Transformer (machine learning model)
- Трансформер (модель машинного обучения)
- Трансформеры используются в Яндекс.Переводчике, Яндекс.Новостях, Google Переводчике, GPT-3.
- Трансформер (модель машинного обучения)
- Transformer (machine learning model)
- YouTube
- Transformers from the Ground Up by Sebastian Raschka
- Medium / Drawing the Transformer Network from Scratch (Part 1) by Thomas Kurbiel
- LessWrong.com
- Can you get AGI from a Transformer? by Steven Byrnes
- Modern Transformers are AGI, and Human-Level by abramdemski
Courses
- A list of publicly-accessible courses from CMU, ranging from machine learning to computer systems to CS theory by Fan Pu Zeng
- 36-708 Statistical Machine Learning, Spring 2018 by Larry Wasserman
- CS281: Advanced Machine Learning
Papers
- Хабр / 50 исследований на тему нейросетей, которые помогут вам стать ИИ-инженером от бога
- Could an FFT be used to speed up a CNN. Yep, there’s already literature on that
Bayesian Nonparametrics
- A Bayesian nonparametric model is a Bayesian model on an infinite-dimensional parameter space. The parameter space is typically chosen as the set of all possible solutions for a given learning problem.
- Bayesian nonparametrics goes a step further by providing models whose complexity grows with the size of the data. We expect to see, e.g., a greater diversity of topics as we read more documents from a news publication, a greater diversity of image subjects as we view more photographs online, and more friend groups as we examine more individuals participating in a social network. Bayesian nonparametrics provides modeling solutions in all of these cases by replacing the finite-dimensional prior distributions of classical Bayesian analysis with infinite-dimensional stochastic processes.
- Nonparametric Bayes by Yee Whye Teh
- Tutorials on Bayesian Nonparametrics by Peter Orbanz
- Non-parametric Bayesian Models by Zoubin Ghahramani
- Bayesian Nonparametrics by Michael I. Jordan
Neural networks
- implement Neural Networks entirely from scratch
- Пикабу / Лучшие курсы по работе с нейросетями
- Naked-Science.ru / Ученые обнаружили предел полезности данных для обучения нейросетей