Handson ML3 is a GitHub repository or organization with source code, releases, documentation, or project resources.
A site offering course notes and learning material for Stanford artificial intelligence and deep learning classes. It lists primers on topics such as transformers, attention and retrieval augmented generation, alongside links to Stanford CS229, CS230, CS231n and CS224n.
A staged learning roadmap for machine learning that covers mathematics and calculus, programming, and machine learning concepts. It advises moving to the next stage only after fully understanding the current one. The mathematics section covers linear algebra, calculus, and probability and statistics, and the programming section covers Python basics and advanced Python.
Deep Learning Drizzle is a collection of links to university and instructor lecture materials on deep learning and related machine learning topics. It lists courses by title, instructor or institution, course webpage, lecture videos and year. Topics include neural networks, natural language processing, computer vision, reinforcement learning, Bayesian deep learning, medical imaging and graph neural networks.
Everything AI/ML is a curated cheatsheet of learning resources covering topics such as generative AI, machine learning, agentic AI, prompt engineering, RAG, fine-tuning and MLOps. It organizes resources into sections, key concepts, interactive visualizations, building blocks and a roadmap from beginner to advanced, with links to external courses, tutorials and documentation.
Machine Learning Visualized is a book of Jupyter Notebooks that implement and mathematically derive machine learning algorithms from first principles. Each notebook's output is a visualization of the algorithm during training, converging at its optimal weights. Chapters cover optimization, clustering and reduction, linear models and activation functions, and neural networks.
Stanford Engineering Everywhere is an online offering of Stanford engineering courses available to students and educators at no charge. Its course portfolio includes a three-course Introduction to Computer Science sequence and more advanced courses in artificial intelligence and electrical engineering. Lecture videos can be streamed or downloaded, and full course materials include syllabi, handouts, homework and exams.
Community notes
Be the first to share how this project worked for you.
Sign in with a verified account to leave a review or join the discussion.
Sign in to reviewKeep exploring
A site offering course notes and learning material for Stanford artificial intelligence and deep learning classes. It lists primers on topics such as transformers, attention and retrieval augmented generation, alongside links to Stanford CS229, CS230, CS231n and CS224n.
A staged learning roadmap for machine learning that covers mathematics and calculus, programming, and machine learning concepts. It advises moving to the next stage only after fully understanding the current one. The mathematics section covers linear algebra, calculus, and probability and statistics, and the programming section covers Python basics and advanced Python.
Deep Learning Drizzle is a collection of links to university and instructor lecture materials on deep learning and related machine learning topics. It lists courses by title, instructor or institution, course webpage, lecture videos and year. Topics include neural networks, natural language processing, computer vision, reinforcement learning, Bayesian deep learning, medical imaging and graph neural networks.
Everything AI/ML is a curated cheatsheet of learning resources covering topics such as generative AI, machine learning, agentic AI, prompt engineering, RAG, fine-tuning and MLOps. It organizes resources into sections, key concepts, interactive visualizations, building blocks and a roadmap from beginner to advanced, with links to external courses, tutorials and documentation.
Machine Learning Visualized is a book of Jupyter Notebooks that implement and mathematically derive machine learning algorithms from first principles. Each notebook's output is a visualization of the algorithm during training, converging at its optimal weights. Chapters cover optimization, clustering and reduction, linear models and activation functions, and neural networks.
Stanford Engineering Everywhere is an online offering of Stanford engineering courses available to students and educators at no charge. Its course portfolio includes a three-course Introduction to Computer Science sequence and more advanced courses in artificial intelligence and electrical engineering. Lecture videos can be streamed or downloaded, and full course materials include syllabi, handouts, homework and exams.
