Awesome AI Learn World

A curated catalog of AI learning resources — courses and the papers, books and docs that go with them — grouped by skill.

Every resource here meets the inclusion criteria: official source, a verifiable author, free or free to audit, still relevant, and teaching concepts rather than button clicks. The same catalog powers AI Learn World, where you can drop any of these onto your own learning board and track your progress.

Contents

• Learning Paths
• AI Foundations
• Machine Learning
• Deep Learning
• Computer Vision
• NLP
• LLMs
• Generative AI
• AI Agents
• Reinforcement Learning
• MLOps
• ML Systems
• Math
• Programming
• Computer Systems
• Databases
• Backend
• DevOps
• Data Engineering
• Technical Writing
• Staying Current

Learning Paths

Ready-made routes through the catalog, stage by stage. On AI Learn World you can start your board from one of them.

Hello AI World

The whole map in one board: programming and math, machine learning, deep learning, then large language models, ML systems or computer vision — and interview prep at the end. Pick the branch that matches the job you want.

Programming

1. Programming — You can write, test and debug a Python program on your own.
   • CS50's Introduction to Programming with Python
2. Data Structures & Algorithms — You can implement common data structures and algorithms, analyze their running time, and choose the right one for a problem.
   • 6.006 Introduction to Algorithms
3. Python for Data — You can work with NumPy arrays, and load, clean, explore and plot a dataset with pandas in a notebook.
   • Python Programming for Economics and Finance
   • Kaggle Learn: Pandas

Math

1. Calculus — You can take derivatives and partial derivatives, compute a gradient, and apply the chain rule.
   • Precalculus
   • Differential Calculus
   • Multivariable calculus
2. Linear Algebra — You can multiply matrices and explain, geometrically, what a matrix does to a vector.
   • Linear algebra
   • Essence of Linear Algebra
3. Probability & Statistics — You can work with probability, random variables and distributions, and test a hypothesis.
   • Statistics and probability

Machine Learning

1. Core Machine Learning — You can train, evaluate and compare regression and classification models.
   • Machine Learning Crash Course

Deep Learning

1. Neural Networks — You can implement backpropagation from scratch and build a small GPT.
   • Neural Networks
   • Neural Networks: Zero to Hero
2. Practice — You can train an image or text model in PyTorch and explain each step.
   • Practical Deep Learning for Coders
   • Dive into Deep Learning
3. Theory — You can explain why deep networks train: optimization, initialization, regularization and normalization.
   • Understanding Deep Learning
4. Attention — You can explain how attention works and why Transformers replaced recurrent networks.
   • The Illustrated Transformer
5. Generative Models — You can explain how a diffusion model turns noise into an image, and implement one.
   • Practical Deep Learning for Coders part 2: Deep Learning Foundations to Stable Diffusion

Large Language Models

1. Transformers & NLP — You can explain attention and implement a Transformer-based NLP model.
   • CS224N: Natural Language Processing with Deep Learning
2. LLM Training — You can explain pretraining, fine-tuning and LoRA, and fine-tune a small model.
   • Hugging Face LLM Course
3. RAG & Evaluation — You can build a retrieval-augmented app end to end, compare at least two retrieval approaches, and write up where its answers fail.
   • LLM Zoomcamp
4. Agents — You can build an agent that uses tools, and evaluate it.
   • Hugging Face AI Agents Course

ML Systems

This is the beginning of the README. Read the rest at the original. Read the full README ↗