Machine learning resources for developers

Free, short, carefully drawn videos that explain statistics and machine learning one small step at a time: p-values, regression, PCA, random forests, gradient descent, neural networks and transformers. When a textbook formula refuses to make sense, a StatQuest video is usually the quickest way to the intuition behind it.

• AI
• Machine learning

Project Jupyter's free, open source environment for notebooks, code and data. You run code a cell at a time, see tables and charts right under it, and keep your reasoning in Markdown beside the code, which is how most data analysis is explored and shared. Installs with one pip command.

• AI
• Programming
• Machine learning

The standard first textbook for statistical learning, free as a PDF in two editions: ISLR2 with R labs and ISLP with Python labs. It explains regression, classification, resampling, regularisation, trees, SVMs, deep learning and unsupervised learning with the minimum of maths, and ends every chapter with a hands-on lab.

• AI
• Machine learning
• Programming

A path for programmers and students who want to train models on data rather than only call an API: Python for data, the maths you need, data cleaning and features, classical machine learning, honest evaluation, deep learning in PyTorch and production MLOps, with an optional computer vision or NLP stage. By the end you can clean a real dataset, choose and evaluate a classical or deep learning model, and ship it as a reproducible, monitored service. The general focus is about 425 hours; vision or NLP adds a stage.

• AI
• Machine learning
• Programming

The official channel of DeepLearning.AI, founded by Andrew Ng, with lectures from its Coursera programmes including the Deep Learning Specialization and the Machine Learning Specialization, plus recorded events and conversations. The lectures are calm, structured and strong on intuition. It suits beginners and intermediate learners who want a trusted, course-like grounding in machine learning and deep learning.

• AI
• Machine learning

Chip Huyen's 2022 O'Reilly book on everything around the model: business framing, data engineering, training data, feature engineering, evaluation, deployment, distribution shift, monitoring, continual learning and MLOps infrastructure. It explains why models that score well in a notebook fail months after launch. It is for ML engineers, data scientists and engineers moving into ML who need to build systems that keep working in production.

• AI
• Machine learning
• System design
• DevOps

A free nine-week course from DataTalks.Club on putting machine learning models into production: experiment tracking with MLflow, orchestration, batch and streaming deployment, monitoring with Evidently and Grafana, and engineering practice such as testing, CI/CD and Terraform. It ends with an end-to-end project. It is for data scientists and engineers who can train a model but have never shipped or operated one.

• AI
• DevOps
• Machine learning

A modern deep learning textbook by Simon J.D. Prince, published by MIT Press in 2023 and free to download as a PDF. It explains how networks, transformers, diffusion models and reinforcement learning actually work, with clear figures and Python notebooks for every chapter. It suits students and engineers who can run a model but want to understand why it works, without a dense research-level text.

• AI
• Machine learning

Kaggle's public machine learning competitions, from beginner Getting Started and Playground contests to large prize competitions and hackathons. Your predictions are scored against a hidden test set, which quickly shows whether your validation is honest, and shared notebooks let you study how strong practitioners approach the same data. It suits students and engineers who want practice on real datasets with instant, objective feedback.

• AI
• Machine learning
• Programming

A 2020 Cambridge University Press textbook by Marc Peter Deisenroth, A. Aldo Faisal and Cheng Soon Ong, free as a PDF. It covers linear algebra, analytic geometry, matrix decompositions, vector calculus, probability and optimisation, then applies them to linear regression, PCA, Gaussian mixture models and support vector machines. It is for students who want to know exactly why ML methods work, and are ready for more rigour than a video course.

• AI
• Machine learning
• CS fundamentals

A free video series from 3Blue1Brown that explains vectors, matrices, determinants, change of basis and eigenvectors as geometric transformations you can watch happen. It is for students and developers heading into machine learning, graphics or data work who can do matrix arithmetic but do not really see what it means. A few evenings with it make later maths courses and ML papers far easier to follow.

• Machine learning
• CS fundamentals

The book on data wrangling in Python by Wes McKinney, the creator of pandas. The third edition (O'Reilly, 2022) is updated for pandas 2.0 and Python 3.10 and is free to read online, covering NumPy, pandas, cleaning, reshaping, grouping, time series and plotting. It suits students and engineers who want to become fluent at loading and shaping real data before moving on to machine learning.

• AI
• Programming
• Machine learning

Python programming tutorials that go past the basics into machine learning, deep learning, robotics, data analysis and more, taught by Harrison Kinsley. Many series build a working project step by step, from neural networks written from scratch to reinforcement learning agents and self-driving car simulations. It suits learners who know some Python and want to build things with it.

• AI
• Programming
• Machine learning

Free data science, machine learning, deep learning and generative AI courses taught in Hindi by Nitish Singh, founder of CampusX. Long structured playlists such as 100 Days of Deep Learning, Maths for Machine Learning and Generative AI using LangChain explain the intuition and the maths before the code. It suits Hindi and Urdu speaking students who want a patient, course-like path through data science and AI.

• AI
• Machine learning
• Programming

A free three and a half hour lecture by Andrej Karpathy that explains, for a general audience, how models like ChatGPT are built: pretraining data, tokenisation, the neural network, post-training and reinforcement learning. It suits developers and students who use LLMs daily and want a clear mental model of why they hallucinate, struggle with counting letters and behave the way they do.

• AI
• Machine learning

A free, open roadmap by Maxime Labonne in three parts: the maths and neural network fundamentals, the LLM Scientist track on building and fine-tuning models, and the LLM Engineer track on shipping applications with RAG, agents and deployment. Each section links to curated reading, and many topics have Colab notebooks you can run without your own GPU. It suits developers who want to stop treating language models as black boxes.

• AI
• Machine learning

A free course from Hugging Face that teaches what an AI agent is, then how to build one with tools, memory and a reasoning loop, using three frameworks: smolagents, LangGraph and LlamaIndex. It ends with a graded final assignment and a free certificate. It suits Python developers who have called an LLM API but have never built something that plans and takes several steps on its own.

• AI
• Machine learning
• AI agents

A beginner course that gives software engineers and students a clear, practical grounding in modern AI: core concepts, training a simple model, neural networks and deep learning, search algorithms, reinforcement learning, agentic AI, modern tools and prompting, and the ethics and hype around it all. It takes about five hours across 14 chapters with playgrounds and assessments, and needs no prior AI background.

• AI
• Machine learning

A free video course by Andrej Karpathy that builds neural networks from scratch in Python, starting with backpropagation on single numbers and ending with a GPT-style transformer and its tokeniser. It is for programmers who want to understand what deep learning frameworks do underneath, so that training problems stop being a mystery. It needs solid Python and basic calculus.

• AI
• Machine learning
• Programming

fast.ai's free course that teaches deep learning by having you train a working model in the first lesson and explaining the theory afterwards. Part 1 is nine lessons of about 90 minutes covering vision, language, tabular data, recommendation and deployment with PyTorch, fastai and Hugging Face. It suits programmers with about a year of coding who want practical machine learning skills without months of mathematics first.

• AI
• Machine learning
• Programming

Hugging Face's free catalogue of hands-on courses covering large language models, agents, context engineering for code agents, diffusion models, deep reinforcement learning, computer vision, audio and robotics. Each one is taught with the open source libraries much of the field uses, so what you build is directly reusable. It suits developers moving into applied machine learning who learn best by running real models.

• AI
• Machine learning

Google's free, self-paced introduction to machine learning, built around short animated videos, interactive visualisations and Python exercises. It covers regression, classification, working with data, neural networks, embeddings and an introduction to large language models, then how models behave in production. It suits programmers who want the standard foundations and vocabulary in a structured order before moving to a deeper or more hands-on course.

• AI
• Machine learning

A free, diagram-led article by Jay Alammar that explains the transformer architecture step by step: self-attention, multi-head attention, positional encoding, the encoder and decoder stacks, and how the model is trained. It is the standard first read for anyone who has heard that attention is all you need and still does not know what attention does, and takes around an hour.

• AI
• Machine learning

A free course by Goku Mohandas on machine learning as software engineering: designing an ML product, data preparation, training and tracking experiments, tuning, evaluation, serving, testing code, data and models, reproducibility, CI/CD and monitoring. It also has a Foundations track on Python, NumPy, pandas, PyTorch and core deep learning. It suits people who can train a model and now need to build and keep a real ML system running.

• AI
• Machine learning
• DevOps