🌟This guide is free! Support it (and me!) for free:🌟
Welcome to the Machine Learning Road Map: Your guide to learning ML fundamentals for free!
This guide will equip you with:
- Essential ML foundations - Master the mathematical and programming fundamentals that underpin ML.
- Core ML concepts - Understand the key principles and algorithms that drive machine learning.
- Implementation fundamentals - Gain the conceptual knowledge needed to start building ML systems.
- Career preparation - Know the skills that employers value in ML professionals.
This road map is streamlined and focuses on the most important topics from the best ML educators. The goal is simple: to get you to a point where you can confidently explore ML topics independently*.
Before you begin:
Don't forget to subscribe to AI for Software Engineers: The AI newsletter for software engineers.
Please support the authors and creators of these resources! Many of these resources had hundreds of hours put into them. If you purchase a book linked in the advanced topics section, don't forget to leave a review after reading it! Reviews are vital for authors to continue their work. I've linked to social profiles throughout the document as much as I could. You can support the creators of these resources for free by giving them a follow and liking their content.
Let's go! 🚀
Table of Contents
Master Python and essential libraries for data manipulation and analysis.
General Programming
- 📚 CS50 (Intro to Programming and Computer Science) by Harvard
- 📚 Google's Python Class by Google
- 📘 NumPy Tutorial by NumPy Team
- 📘 Pandas Course by Kaggle
Build the mathematical foundation: linear algebra, calculus, and probability.
- 📐 Algebra Curriculum by Khan Academy
- 📐 Linear Algebra by Khan Academy
- 📊 Probability by Harvard
- 📈 Derivatives/Partial Derivatives by Khan Academy
- 📈 Gradients by Khan Academy
- 📈 Backpropagation Visualization by Google
Learn version control and command-line tools essential for any developer.
- 🛠️ Learn Git by Git Community
- 🛠️ Github Tutorial by GitHub
- 🛠️ Learn Shell by learnshell.org
Core Machine Learning
Understand fundamental ML principles and system design patterns.
Learn how large language models work and how to build them from scratch.
Master neural networks and the transformer architecture powering modern AI.
Train agents to make decisions through trial and error in dynamic environments.
- 📚 Spinning Up in RL by OpenAI
Apply ML to understand text and images with state-of-the-art techniques.
- 📚 NLP Course by Huggingface
- 📚 Computer Vision by Kaggle
Explore how ML is applied in scientific research and game development.
- 📘 ML for Science by Christoph Molnar & Timo Freiesleben
- 🎮 ML for Games by Huggingface
Learn to query, clean, and prepare data for machine learning pipelines.
- 📚 Intro to SQL and Advanced SQL by Kaggle
- 📚 Data Preparation by Google
Deploy and maintain ML models in production with MLOps best practices.
- 🛠️ Made with ML by Goku Mohandas
- 🎓 ML School by Santiago
Build real-world applications using LLMs and modern AI tools.
AI Agents
Build autonomous systems that can reason, plan, and execute multi-step tasks using LLMs.
- 📚 AI Agents in LangGraph by DeepLearning.AI
- 📚 Building Agentic RAG with LlamaIndex by DeepLearning.AI
- 📘 LangChain Agents Guide by LangChain
Prompt Engineering
Learn techniques to write effective prompts that get better, more reliable outputs from LLMs.
- 📚 Prompt Engineering for Developers by DeepLearning.AI
- 📘 Prompt Engineering Guide by Anthropic
- 📘 OpenAI Prompt Engineering by OpenAI
Dive deeper into specialized areas like efficiency, ethics, and explainability.
- 📐 ML Mathematics by Tivadar Danka
- 📈 ML Efficiency by MIT
- 📘 Knowledge Distillation by Dmitry Kozlov
- 📚 AI Ethics by Kaggle
- 📚 ML Explainability by Kaggle
This sections contains popular skills on machine learning-related job listings and resources to prepare for interviews for those jobs.
Prepare for coding interviews and ML-specific technical questions.
- Cracking the Coding Interview by Gayle Laakman McDowell
- 📘 System Design Interview by Alex Xu
- Study Plan for ML Interviews by Khang Pham
Deepen your skills in languages commonly used in ML roles.
- 📚 Intro to Python by Harvard
- 📚 Python Deep Dive by Stephen Gruppetta
- 📚 C++ Tutorial by freeCodeCamp
- 📘 Rust by Rust Team
- 📚 Java by University of Helsinki
Master the libraries and tools used to build and train ML models.
Deep Learning
- 📚 TensorFlow 2.0 Complete Course by freeCodeCamp
- 📚 PyTorch for Deep Learning by Daniel Bourke
- 📘 Scikit-learn Tutorials by Scikit-learn Developers
- 📘 Keras Tutorial by TutorialsPoint
Data Processing
- 📘 NumPy Tutorial by NumPy Team
- 📚 Pandas Course by Kaggle
Advanced Tools
- 🛠️ JAX Quickstart by Google
- 🛠️ ONNX Tutorial by ONNX Team
- 🛠️ TensorRT Guide by NVIDIA
- 🛠️ LangChain Crash Course by Patrick Loeber
Model Development
- 📘 XGBoost Documentation by XGBoost Team
- 📘 CUDA Programming Guide by NVIDIA
Learn to deploy and scale ML workloads on major cloud providers.
Major Providers
- 🛠️ ML on Google Cloud by Google Cloud
- 🛠️ AWS Machine Learning by Amazon Web Services
- 🛠️ Azure AI Fundamentals by Microsoft
Containerize and orchestrate ML applications for production deployment.
Top Choices
- 🖥️ Google Colab
Free T4/P100 GPUs, limited time
- 🖥️ Kaggle Notebooks
30 hours/week of P100/T4 GPU
Additional Options
- 🖥️ Lightning AI
22 GPU hours free
- 🖥️ Google Cloud Platform
$300 free credits
- 🖥️ Amazon SageMaker
Free tier available
- 🖥️ Paperspace Gradient
Free community tier
If any information is missing, you are the author of a resource and you'd like it removed, or any other general feedback send me a message to let me know.
