ml-road-map

ml-road-map

The most streamlined road map to learn ML fundamentals for free.

Stars: 253

Visit
 screenshot

The Machine Learning Road Map is a comprehensive guide designed to take individuals from various levels of machine learning knowledge to a basic understanding of machine learning principles using high-quality, free resources. It aims to simplify the complex and rapidly growing field of machine learning by providing a structured roadmap for learning. The guide emphasizes the importance of understanding AI for everyone, the need for patience in learning machine learning due to its complexity, and the value of learning from experts in the field. It covers five different paths to learning about machine learning, catering to consumers, aspiring AI researchers, ML engineers, developers interested in building ML applications, and companies looking to implement AI solutions.

README:

Machine Learning Road Map

ml road map turbo

Welcome to the Machine Learning Road Map. This is the fastest, high-quality road map to get up to speed on machine learning fundamentals. It teaches you the prerequisites and machine learning fundamentals necessary to understand how machine learning works and build with it. The goal is to quickly get to a point where you can comfortably explore machine learning topics on your own. Many other road maps are more comprehensive, this one is purposefully streamlined.

These resources are aggregated from the best ML educators. I've linked to the authors as much as possible. Please support them. Feedback/suggestions/corrections are always welcome and appreciated.

If you're less interested in the technical details of machine learning and want to know more about how machine learning will affect you as a consumer, I've written an article just for that. You can also check out the Google AI Essentials Course learn how to use generative AI to boost your productivity.

To support this project and stay updated:

This road map will be updated as new learning resources are created and new ML topics emerge. Let's get started!


Things to Know Before You Begin

  • Machine Learning will impact everyone's life. It's a new paradigm of computing that will completely change the way consumers expect their devices to work.
  • Machine learning is a rapidly developing field. There are many complex fields within machine learning. Take it slow and don't expect to become an expert in it all.
  • The best way to understand machine learning is to learn from others who understand the topics you want to know more about. I've created a list of accounts to follow on X. I've also aggregated a list of newsletters, blogs, and channels I find helpful to stay updated.

Machine Learning Prerequisites

These prerequisites contain a mixture of math and programming concepts. Feel free to skip things you already understand.

Topic Source Author
Programming
General Programming CS50 Harvard
Python Intro to Python (For Beginners) Harvard
Google's Python Class (Refresher) Google
NumPy NumPy Tutorial NumPy Team
Pandas Pandas Course Kaggle
Math
Algebra Algebra Curriculum Khan Academy
Linear Algebra Linear Algebra Curriculum Khan Academy
Probability Uncertainty Section of CS50 Harvard
Calculus Derivatives/Partial Derivatives Khan Academy
Gradients Khan Academy
Backpropagation Visualization Google
Tools
Version Control Learn How to Use Git Open Source Git Community
Github Tutorial GitHub
Terminal Learn Shell learnshell.org

Machine Learning Fundamentals

This is the main material. Complete these to understand machine learning fundamentals:

Topic Source Author
Intro 20 Min Introduction to Machine Learning Google
Fundamentals Machine Learning Crash Course Google

Advanced ML Topics

High-quality resources to explore more advanced topics that are helpful for machine learning:

Topic Source Author Type
General Advanced ML Topics Machine Learning Q and AI Sebastian Raschka Book
Large Language Models Intro to LLMs Andrej Karpathy Video
Developing, Building, and Fine-tuning a LLM Sebastian Raschka Video
Build a Large Language Model (From Scratch) Sebastian Raschka Book/Repo
Quantization Section of LLM Course Maxime Labonne Course/Repo
LLM Tools Maxime Labonne Course/Repo
LLM Engineering Maxime Labonne Course/Repo
LLM Engineer's Handbook Paul Iusztin, Maxime Labonne, Alex Vesa Book
Generative AI Generative AI For Beginners Microsoft Course/Repo
Natural Language Processing (NLP) NLP Course Huggingface Course
Transformers Start of NLP Course Huggingface Course
Deep Learning Deep Learning Fundamentals LightningAI Course
Deep Learning Book Ian Goodfellow and Yoshua Bengio and Aaron Courville Book
The Engineer's Guide To Deep Learning Hironobu Suzuki Book
Reinforcement Learning (RL) Spinning Up OpenAI Course
Computer Vision Computer Vision Kaggle Course
Unsupervised Learning Second Half of CS229 Andrew Ng/Stanford Lecture
Supervised Learning Supervised Machine Learning for Science Christoph Molnar & Timo Freiesleben Book
ML for Video Games Machine Learning for Games Huggingface Course
Feature Engineering Data Prep Google Course
AI Ethics Intro to AI Ethics Kaggle Course
ML Explainability Machine Learning Explainability Kaggle Course
ML Ops Made with ML Goku Mohandas Course
Virtual Classroom for Building LLMs ML School Santiago Interactive Course
More Python The Python Coding Place Stephen Gruppetta Website/Book
SQL Intro to SQL Kaggle Course
Advanced SQL Kaggle Course
Studying for ML Interviews Study Plan for ML Interviews Khang Pham Repo
Machine Learning Math Mathematics of Machine Learning Tivadar Danka Book
Machine Learning Efficiency EfficientML.ai Lecture MIT Course
Knowledge Distillation Awesome Knowledge Distillation Dmitry Kozlov Repo
System Design System Design Interview Volume 1 and Volume 2 Alex Xu Book

Your support helps keep this resource up-to-date and valuable for the ML community!

Job Skills and Where to Learn Them

This section contains the technologies and skills I find most often as I go through real machine learning-related job descriptions and the resources for learning each.

Topic Source Author
Tensorflow TensorFlow 2.0 Complete Course freeCodeCamp
PyTorch PyTorch for Deep Learning Daniel Bourke
Scikit-learn Scikit-learn Tutorials Scikit-learn Developers
Keras Keras Tutorial TutorialsPoint
NumPy NumPy Tutorial NumPy Team
Pandas Pandas Course Kaggle
SQL Intro to SQL Kaggle
Python Intro to Python (For Beginners) Harvard
C++ C++ Tutorial for Beginners freeCodeCamp
Rust The Rust Programming Language Rust Team
JAX JAX Quickstart Google
Linear Algebra Linear Algebra Curriculum Khan Academy
Calculus Essence of Calculus 3Blue1Brown
Deep Learning Deep Learning Fundamentals LightningAI
Computer Vision Computer Vision Kaggle
Natural Language Processing NLP Course Huggingface
ONNX ONNX Tutorial ONNX Team
TensorRT TensorRT Developer Guide NVIDIA
LangChain LangChain Crash Course Patrick Loeber
AWS AWS Machine Learning Amazon Web Services
Azure Azure AI Fundamentals Microsoft
GCP Machine Learning on Google Cloud Google Cloud
XGBoost XGBoost Documentation XGBoost Team
Transformers Transformers Course Hugging Face
CUDA CUDA C++ Programming Guide NVIDIA
Java Java Programming University of Helsinki
LLMs Building LLMs from the Ground Up Sebastian Raschka
RAG Building RAG-based LLM Applications for Production DeepLearning.AI
Kubernetes Kubernetes Tutorial for Beginners TechWorld with Nana
Docker Docker Tutorial for Beginners freeCodeCamp

Newsletters, Blogs, and Channels for Machine Learning

All of these are must-subscribes:

Resource Author
Blogs/Newsletters
Ahead of AI Sebastian Raschka
AI Made Simple Devansh
Society's Backend Logan Thorneloe
The Batch Andrew Ng
Interconnects Nathan Lambert
Deep (Learning) Focus Cameron R. Wolfe
ML Spring Akshay Pachaar
Spatial Intelligence Bilawal Sidhu
The AIEdge Damien Benveniste
Google DeepMind Blog Multiple
OpenAI Blog Multiple
Meta AI Blog Multiple
QiuByte Hesam Sheikh
NLP Newsletter Elvis
The Palindrome Tivadar Danka
YouTube
Andrej Karpathy Andrej Karpathy
Spatial Intelligence Bilawal Sidhu
Jay Alammar Jay Alammar
Mervin Praison Mervin Praison
Nicholas Renotte Nicholas Renotte
Jeremy Howard Jeremy Howard
Logan Thorneloe Logan Thorneloe
3Blue1Brown Grant Sanderson
RohanPaulAI Rohan Paul

For a list of almost all the available ML YouTube Courses check out this repo by Dair AI.

Free GPUs for Training

I've aggregated a list of cloud providers that offer a free tier for training machine learning models. Anyone can get started with ML- you don't need a powerful local machine. If anything is incorrect, reach out to me on X so I can make the fix. If there is a cloud computing platform that I've missed, also let me know.

Resource Details
Top Choices
Google Colab Offers free access to GPUs (usually NVIDIA T4 or P100) and TPUs with limited usage time and resources. Excellent for small projects and experimentation.
Kaggle Notebooks Provides 30 hours/week of GPU usage (NVIDIA Tesla P100 or T4) for free. It's a good option with access to Kaggle's datasets and community.
Other Options
Lightning AI Offers one free studio with 22 GPU hours and is pay-as-you-go after that.
Google Cloud Platform Offers $300 in free credits to new users.
Amazon SageMaker Provides a free tier with limited access to various machine learning resources.
Paperspace Gradient Offers a free community tier with access to limited GPU resources for experimentation and learning.

Support This Guide

Don't forget to star this repo and follow me on X to support this guide. Please support the authors of these resources by following them at the links I included. You can also find them in my ML on X list.

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.

For Tasks:

Click tags to check more tools for each tasks

For Jobs:

Alternative AI tools for ml-road-map

Similar Open Source Tools

For similar tasks

For similar jobs