Welcome to my AI Learning Roadmap! I created this based on my own journey—building projects, getting stuck, learning from mistakes, and sharing what’s actually useful. This started as something for my personal use, but it’s grown into a resource for anyone hungry to break into AI, whether you’re a student, a mid-career dev, a maker, or just curious about artificial intelligence.
- For everyone: If you have basic math and coding, you’ll find a path here. No advanced degree needed—just willingness to learn.
- Free & open: Every resource is free and open for anyone. All you need is internet access and some curiosity.
- Step-by-step, but flexible: I organized this in a way that helps most people, but feel free to skip ahead or backtrack as you go.
- Practical focus: Instead of endless theory, this guide sticks to what you truly need for real projects and understanding—90% impact, less busywork.
- Community powered: Learning is way better (and more fun) together. Consider joining our Discord or any active ML community.
- Always up to date: I regularly add new courses, tools, and project ideas as AI keeps growing.
🛠 Building, tinkering, and learning actively is the heart of this journey. Dive in, start small, build things, and share your wins and struggles.
Why:
AI is built on code, and Python is the main language in this field. Even if you’re not aiming to become a full-time developer, getting comfortable with Python and version control will make your life a lot easier.
Resources:
- Python for Beginners by Mosh
- Google’s Python Class
- Automate the Boring Stuff with Python (Book)
- Learn Git from Mosh
- How to Create a Python Virtual Environment
- Kaggle Learn: Python
- PyTorch Beginner Series
Why:
Math isn’t something to fear in AI—but a good grasp of linear algebra, calculus, and probability helps you move beyond running code and truly understand how models work.
Resources:
Why:
AI is only as useful as your ability to communicate and visualize your results clearly. This is what turns insights into impact.
Resources:
Why:
Here’s where it all comes together. Start building and dissecting real models. Don’t just watch—implement!
Resources:
- Machine Learning by StatQuest (Josh Starmer)
- fast.ai: Practical Deep Learning for Coders
- Google ML Crash Course
- Kaggle Learn: Machine Learning
Practice:
- Implement classic models in PyTorch:
- Linear Regression
- Logistic Regression
- KNN
- Decision Trees
- Random Forest
- Gradient Boosting
Why:
Deep learning powers breakthroughs in vision, language, generative AI, and more. Hands-on practice is key.
Resources:
- Deep Learning by StatQuest
- Neural Networks by 3Blue1Brown
- PyTorch Deep Learning Tutorial Series
- Andrej Karpathy’s Neural Networks: Zero to Hero
- DeepLearning.AI Short Courses
Why:
AI is a fast-moving field. The best way to stay sharp is to build, read, connect, and share.
Resources:
- Kaggle Learn Tracks
- Papers with Code
- mlc.ai – Research & Project Ideas
- Build Your Own X (Machine Learning Section)
- Awesome Machine Learning (GitHub)
The AI landscape is moving quickly, but these core concepts and tools have helped me—and thousands of others—get started and keep growing.
The real progress comes when you code, experiment, break things, and share your journey.
Don’t stress about following the roadmap perfectly; your path will be unique, with plenty of detours and discoveries along the way.
Whether you want to build the next generation of AI products, contribute to open source, or just satisfy your curiosity, this roadmap is your foundation.
Good luck, and have fun building! 🚀