Roadmap to Learn AI in 2024

medium.com/bitgrit-data-science-publication/a-roadmap-to-learn-ai-in-2024-cc30c6aa6e16

Top highlight

Want to learn AI?

A free curriculum for hackers and programmers to learn AI

made with excalidraw

So, you want to learn AI? But you don’t know how or where to get started?

I wrote the Top 20 free Data Science, ML, and AI MOOCs on the Internet back in 2020. But I’ve realized that
doing many courses isn’t the way.

1/14
To escape tutorial hell and learn, you have to get hands-on, write algorithms from scratch, implement
papers, and do fun side projects using AI to solve problems.

This article attempts to craft a free curriculum that follows that philosophy. I’m working on some of these
courses, so on or if you want to learn together!

Also, leave a comment if you think it’s missing anything!

But first, a few notes on the curriculum and some advice on learning.

Top-down approach
This curriculum follows a top-down approach — code first, theory later.

I like to learn out of necessity. So, if I have to figure out something, a problem to solve, or a prototype to
make, I will reach far and wide for the information I need, study, make sense of it, and then act on it.

For example, I aim to be an AI engineer who understands LLMs at a fundamental level, which involves
having the skill to code transformers from scratch and fine-tuning LLMs on GPUs, etc. I can’t do that now
because there are gaps in my knowledge, and I aim to fill in those gaps.

It is also NLP-focused; if you’re looking for other AI specializations like computer vision or reinforcement
learning, comment below or DM me on or . I will pass you some recommendations.

Before I dump a bunch of links on you, I wish somebody had told me two important things before I started
learning anything.

Learn in Public
There’s a lot to learn, and you will never be done learning, especially with AI, when new revolutionary papers
and ideas are released weekly.

The biggest mistake you can make is to learn in private. You don’t create any opportunities for yourself if you
do that. You don’t have anything to show for it besides being able to say you completed something. What
matters more is what you made of the information, how you turned it into knowledge to be shared with the
public, and what novel ideas and solutions came from that information.

So, you should .

That means having a habit of creating.

This can mean:

writing blogs and tutorials

join hackathons and collaborate with others

2/14
 ask and answer questions in Discord communities
work on side projects you’re passionate about
tweeting about something interesting you discovered new

And speaking about Twitter,

Use Twitter
If you follow the right people and use it right, Twitter is the highest-value social platform anyone can be on
today.

Who to follow? See this AI list by Suhail.

How to use Twitter? Read Near’s How to Twitter Successfully.

DM people on Twitter. Be sincere, keep it short, and have a specific ask. This guide on How to write a cold
email by Sriram Krishnan can also apply to DMs.

How to tweet? Read Anatomy of a Tweet by Jason, creator of Instructor, who grew from 0 → 14k followers
in months.

If you’re reading this, !

about what you’re up to! I’m always up for collaborating on cool projects.

Now let’s get into it.

Mathematics

3/14
 DALL·E

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.

the mathematical toolkit for data representation and manipulation, where matrices and vectors form the
language for algorithms to interpret and process information
The engine for optimization in machine learning, enabling algorithms to learn and improve by
understanding gradients and rates of change.
The foundation for decision-making under uncertainty, allowing algorithms to predict outcomes and
learn from data through models of randomness and variability.

4/14
This is a great series on Math for ML from a programmer’s perspective: (code)

If you want a code-first approach to Linear Algebra, do (video, code) by the creators of fast.ai.

Read alongside the course.

If you want something more traditional, look at Imperial College London lectures — Linear Algebra &
Multivariate Calculus.

Watch 3Blue1Brown’s and .

Watch by StatQuest for statistics

Supplementary

Book:
Paper:

Tools

5/14
 DALL·E

Python
Beginners start here: .

If you’re already comfortable with Python, do this

They’re both great courses by David Beazley, author of Python Cookbook.

After that, watch some of talks

Read Python Design Patterns.

Supplementary

Book: ()
Podcasts: &

PyTorch

6/14
Videos

by

Official

Practice

Supplementary

Book:

Machine Learning

DALL·E

Read the 100-page ML book.

Write from Scratch

While you’re reading, write the algorithms from scratch.

Look at the repositories below

If you want a challenge, write PyTorch from scratch by following this course.

7/14
 (, )

Compete
Apply what you learn in competitions.

Join ML competitions on platforms like and ; find more in .

Look at and study them

Do side projects
Read Getting machine learning to production by Vicki Boykis

She also wrote about what she learned building Viberary, a semantic search for books.

Get a dataset and build a model (i.e., use earthaccess to get NASA Earth data).

Deploy them
Get the models in production. Track your experiments. Learn how to monitor models. Experience data and
model drift firsthand.

Here are some excellent resources

Supplementary
()

Deep Learning

8/14
If you want top-down, start with fast.ai.

Fast.ai
fast.ai (, ) +

Liked fast.ai? Check out Full Stack Deep Learning.

If you want a more comprehensive, traditional course, check out UNIGE 14x050 — Deep Learning by
François Fleuret.

If you need to reach for theory at some point, these are great books.

(has code examples in PyTorch, NumPy/MXNet, JAX, and TensorFlow)

by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
(with hands-on )

Read on your phone instead of scrolling Twitter.

Read these while your neural networks are converging.

Do more competitions
(computer vision)

9/14
Implement papers
Check out labml.ai Annotated PyTorch Paper Implementations

Papers with Code is a great resource; here’s BERT explained on their website.

Below are some resources for the specializations within Deep Learning

Computer Vision
A lot of people recommend CS231n: Deep Learning for Computer Vision. It’s challenging but worth it if you
get through it.

Reinforcement Learning
For RL, these two are great:

by OpenAI

NLP
Another great Stanford course, CS 224N | Natural Language Processing with Deep Learning

Learn Hugging Face: Hugging Face NLP Course

Good articles and breakdowns

Supplementary

Large Language Models

10/14
First, watch [1hr Talk] Intro to Large Language Models by Andrej.

Then Large Language Models in Five Formulas, by Alexander Rush — Cornell Tech

Watch Neural Networks: Zero to Hero

It starts with explaining and coding backpropagation from scratch and ends with writing GPT from scratch.

He just released a new video →

You can also look at GPT in 60 Lines of NumPy | Jay Mody while you’re at it.

Free LLM boot camp

A paid LLM Bootcamp released for free by Full Stack Deep Learning.

It teaches prompt engineering, LLMOps, UX for LLMs, and how to launch an LLM app in an hour.

Now that you’re itching to build after this boot camp,

Build with LLMs

Want to build apps with LLMs?

Watch Application Development using Large Language Modelsby Andrew Ng

11/14
Read by Huyen Chip

As well as by Eugene Yan

Refer to the OpenAI Cookbook for recipes.

Use Vercel AI templates to get started.

Participate in hackathons
lablab.ai has new AI hackathons every week. Let me know if you want to team up!

If you want to go deeper into the theory and understand how everything works:

Read papers
A great article by Sebastian Raschka on Understanding Large Language Models, where he lists some
papers you should read.

He also recently published another article with papers you should read in January 2024, covering mistral
models.

Follow his substack Ahead of AI.

Write Transformers from scratch.

Read The Transformer Family Version 2.0 | Lil’Log for an overview.

Choose whichever format suits you best and implement it from scratch.

Paper

by Harvard

Blogs

() ()
by

Videos

You can code transformers from scratch now. But there’s still more.

Watch these videos.

12/14
Some good blogs
by Eugene Yan

Watch Umar Jamil

He has fantastic in-depth videos explaining papers. He also shows you the code.

Some more links related to LLMs that are not exhaustive. Look at for a more comprehensive syllabus for
LLMs.

Learn how to run open-source models.

Use ollama: Get up and running with Llama 2, Mistral, and other large language models locally

They recently released Python & JavaScript Libraries

Prompt Engineering
Read Prompt Engineering | Lil’Log

ChatGPT Prompt Engineering for Developers by Ise Fulford (OpenAI) and Andrew Ng

DeepLearning.ai also has other short courses you can enroll in for free.

Fine-tuning LLMs
Read the Hugging Face fine-tuning guide.

A good guidebook: Fine-Tuning — The GenAI Guidebook

Check out axolotl.

This is a good article: Fine-tune a Mistral-7b model with Direct Preference Optimization | by Maxime
Labonne

RAG
A great article by Anyscale: Building RAG-based LLM Applications for Production

A comprehensive overview of Retrieval Augmented Generation by Aman Chadha

I’ve spent enough time writing and organizing this that it’s diminishing returns. It’s time to learn and build.

I hope this will help you in your AI journey!

13/14
If you’ve read this far, don’t forget to reach out or leave a comment :)

Be sure to follow the to keep updated!

Want to discuss the latest developments in Data Science and AI with other data scientists? !

Follow Bitgrit below to stay updated on workshops and upcoming competitions!

14/14