So, you're interested in learning AI, but unsure of where to start?
The key to truly learning and escaping the so-called tutorial hell is to immerse yourself: write algorithms from scratch, implement research papers, and engage in fun side projects using AI to solve problems.
This article presents a free curriculum that aligns with this philosophy. Feel free to reach out to me on Twitter if you'd like to learn together!
Don't hesitate to leave a comment if you think something is missing!
Before we delve in, let's discuss the curriculum and provide some learning advice.
Top-down approach
This curriculum follows a top-down approach — prioritize coding, with theory to follow.
I believe in learning out of necessity. If there's a problem to solve or a prototype to create, I will gather the necessary information, understand it, and then act on it.
For instance, my goal is to become an AI engineer who fundamentally understands Language Model Learning (LLM), which requires the ability to code transformers from scratch and fine-tune LLMs on GPUs, among other things.
Learn in Public
Learning is a never-ending process, especially in AI, where new revolutionary ideas and papers are published weekly.
The biggest mistake you can make is to learn in isolation. It limits your potential opportunities. It's not just about completing a course or a book, but about how you've transformed the information into shareable knowledge and how it has inspired new ideas and solutions.
This involves cultivating a habit of creating.
For example, you can:
- Write blogs and tutorials
- Participate in hackathons and collaborate with others
- Ask and answer questions in Discord communities
- Work on side projects you're passionate about
And speaking of social platforms,
Use Twitter (X)
When used correctly and with the right network, Twitter can be one of the most valuable social platforms today.
Machine learning relies heavily on three pillars of mathematics: linear algebra, calculus, probability, and statistics. Each plays a unique role in enabling algorithms to function effectively.
- Linear Algebra: the mathematical toolkit for data representation and manipulation, where matrices and vectors form the language for algorithms to interpret and process information
- Calculus: The engine for optimization in machine learning, enabling algorithms to learn and improve by understanding gradients and rates of change.
- Probability and Statistics: The foundation for decision-making under uncertainty, allowing algorithms to predict outcomes and learn from data through models of randomness and variability.
This is a great series on Math for ML from a programmer’s perspective: Math for Machine Learning by Weights & Biases (code)
If you want a code-first approach to Linear Algebra, do Computational Linear Algebra (video, code) by the creators of fast.ai.
Read Introduction to Linear Algebra for Applied Machine Learning with Python alongside the course.
Watch 3Blue1Brown’s Essence of Linear Algebra and Essence of Calculus.
Watch Statistics Fundamentals by StatQuest for statistics
Supplementary
