2020 Machine Learning Roadmap (87% valid for 2024)

Getting into machine learning is quite the adventure. And as any adventurer knows, sometimes it can be helpful to have a compass to figure out if you're heading in the right direction.

Although the title of this video says machine learning roadmap, you should treat it as a compass. Explore it, follow your curiosity, learn something and use what you learn to create your next steps.

Links:

Timestamps:
0:00 - Hello & logistics
0:57 - PART 0: INTRO
1:42 - Brief overview of topics
3:05 - What is machine learning?
4:37 - Machine learning vs. traditional programming
7:41 - Why use machine learning?
8:44 - The number 1 rule of machine learning
10:45 - What is machine learning good for?
14:27 - How Tesla uses machine learning
17:57 - What we're going to cover in this video
20:52 - PART 1: Machine Learning Problems
22:27 - Categories of learning
26:17 - Machine learning problem domains
29:04 - Classification
33:57 - Regression
39:35 - PART 2: Machine Learning Process
41:57 - 6 major steps in a machine learning project
43:57 - Data collection
49:15 - Data preparation
1:04:00 - Training a model
1:23:33 - Analysis/evaluation
1:26:40 - Serving a model
1:29:09 - Retraining a model
1:30:07 - An example machine learning project
1:33:15 - PART 3: Machine Learning Tools
1:34:20 - Machine learning tools overview
1:38:36 - Machine learning toolbox (experiment tracking)
1:39:54 - Pretrained models for transfer learning
1:41:49 - Data and model tracking
1:43:35 - Cloud compute services
1:47:07 - Deep learning hardware (build your own deep learning PC)
1:47:53 - AutoML (automatic machine learning)
1:51:47 - Explainability (explaining the outputs of your machine learning model)
1:53:38 - Machine learning lifecycle (tools for end-to-end projects)
1:59:24 - PART 4: Machine Learning Mathematics
1:59:37 - The main branches of mathematics used in machine learning
2:03:16 - How I learn the math for machine learning
2:06:37 - PART 5: Machine Learning Resources
2:07:17 - A warning
2:08:42 - Where to start learning machine learning
2:14:51 - Made with ML (one of my favourite new websites for ML)
2:16:07 - Wokera ai (test your AI skills)
2:17:17 - A beginner-friendly path to start machine learning
2:19:02 - An advanced path for learning machine learning (after the beginner path)
2:21:43 - Where to learn the mathematics for machine learning
2:22:23 - Books for machine learning
2:24:27 - Where to learn cloud services
2:24:47 - Helpful rules and tidbits of machine learning
2:26:05 - How and why you should create your own blog
2:28:29 - Example machine learning curriculums
2:30:19 - Useful machine learning websites to visit
2:30:59 - Open-source datasets
2:31:26 - How to learn how to learn
2:32:57 - PART 6: Summary & Next Steps

Connect elsewhere:

#machinelearning #datascience

[mrdbourke]

**2024 Update:** Hello hello! Welcome to the 2020 machine learning roadmap! A few people have asked, "is this still valid for 2024"?

The short answer: yes, mostly.

However, it does not include anything on LLMs or generative AI.

When I made this, LLMs and generative AI were still being figured out. Now they work. Really well.

Not to worry!

A new roadmap is in the planning stage.

I'll update this comment as more progress gets made.

Leave a reply if there's anything in particular you'd like to see :)

In the meantime, happy machine learning!

[ambarishkapil]

Daniel you, my friend, are a legend. It's so good to see such passion and enthusiasm for your craft, and the ML community is glad to have someone like you blazing a trail so that the new members can follow.

[uzaykaradag]

Presentations in the technical field such as this rarely have this much quality knowledge packed into them but it's even rarer that they are this aesthetically pleasing!

[taejunoh]

I've never left a comment on YouTube, but I feel like I MUST DO after watching this video. It is very organized and useful to understand how we approach ML and keep learning it. I appreciate you made this great one.

[라면먹고싶다-dw]

This was literally mind blowing, thank you for taking time to create the roadmap. I'm a junior at a university studying CS, and I just decided during my sophomore summer quarter that I want to specialize in machine learning/data science. But it's been overwhelming and I feel I don't have much time left since I'm already starting as a junior. I hope I can make it out alive and successful; Im gonna utilize all your resources and books and courses in the best of my abilities. Cheers!

[mrdbourke]

Hey there! Happy New Year! Speaking of the new year, you might be wondering "is this still valid for 2021?" and the answer is yes, it's still valid for 2021.


All of the main concepts remain valid for the new year.

If anything changes drastically, I'll look to update/make a new version of this video.

In the meantime, happy machine learning!

[JedidiJedidi]

You just contributed to make the world a better place!!!
I wish if there is a roadmap like that for every subject in the world.

[KenJee_ds]

Looking forward to this my friend! Great thumbnail 😉

[TheMrInnokenty]

finally after 8 years of watching videos, youtube has recommended smth really good)!

[zohairniroomand]

Finally someone explains ML in an understandable, fun way with a lovely accent :)

[anubratabhowmick]

This is probably the best roadmap ever!
Best 2 hrs and 30 minutes ever spent!

[leosiemens]

This is probably one of the best videos out there, congratulations! Perfect compass!

[kesavae]

Best thing happened to me so far in 2020😌

[lagseeing]

First time I watched a 2h+ video without sleep all the way to the end.

[zlla]

I really like your organization reminds me of a visual representation of what a tool box would look like to a mechanic

[keith]

Really Really Really appreciate the time and effort you put into these videos by researching and providing the right info for people to enter the Machine learning space! Keep up the great work man! Cheers.

[chriscockrell]

"Data and Model preparation" would make sense from a process perspective. Collection and preparation are not steps of a process of building ML system. (Many of the subheading aren't process either, but concepts and their explanations for understanding.)
I love the concept map and it's graph theory connectivity.

Great teaching material. Truly inspirational. I've been looking at Data Analytics, Machine Learning, Neural Networks, Artificial Intelligence, and Time Series modeling for a while now as an effort to narrow down a PhD dissertation topic, and this really pulls together a lot that I've come to understand and see differently since starting this journey. This is such a great narration of ML that I'll have to watch it again and improve my notes.

I've been exploring the nature of data to see about other angles of attack and I'm impressed at many of your summaries. I've looked a lot at graphs and the information they convey. I've explored your data types in depth. Nominal, ordinal, interval, numerical. Time series has been an interesting dimension as it forces you to see that people can only conceptualize and create systems that are discrete. We have to break a continuous reality (data) into discrete concepts like a person (or an object to be more precise, like the ship of thesius concept, if you cut off my hand, am I still me?) or a word (with an essences of structured properties and characteristics).

Timestamps:

0:00 - Hello & logistics
0:57 - PART 0: INTRO
1:42 - Brief overview of topics
3:05 - What is machine learning?
4:37 - Machine learning vs. traditional programming
7:41 - Why use machine learning?
8:44 - The number 1 rule of machine learning
10:45 - What is machine learning good for?
14:27 - How Tesla uses machine learning
17:57 - What we're going to cover in this video
20:52 - PART 1: Machine Learning Problems
22:27 - Categories of learning
26:17 - Machine learning problem domains
29:04 - Classification
33:57 - Regression
39:35 - PART 2: Machine Learning Process
41:57 - 6 major steps in a machine learning project
43:57 - Data collection
49:15 - Data preparation
1:04:00 - Training a model
1:23:33 - Analysis/evaluation
1:26:40 - Serving a model
1:29:09 - Retraining a model
1:30:07 - An example machine learning project
1:33:15 - PART 3: Machine Learning Tools
1:34:20 - Machine learning tools overview
1:38:36 - Machine learning toolbox (experiment tracking)
1:39:54 - Pretrained models for transfer learning
1:41:49 - Data and model tracking
1:43:35 - Cloud compute services
1:47:07 - Deep learning hardware (build your own deep learning PC)
1:47:53 - AutoML (automatic machine learning)
1:51:47 - Explainability (explaining the outputs of your machine learning model)
1:53:38 - Machine learning lifecycle (tools for end-to-end projects)
1:59:24 - PART 4: Machine Learning Mathematics
1:59:37 - The main branches of mathematics used in machine learning
2:03:16 - How I learn the math for machine learning
2:06:37 - PART 5: Machine Learning Resources
2:07:17 - A warning
2:08:42 - Where to start learning machine learning
2:14:51 - Made with ML (one of my favourite new websites for ML)
2:16:07 - Wokera ai (test your AI skills)
2:17:17 - A beginner-friendly path to start machine learning
2:19:02 - An advanced path for learning machine learning (after the beginner path)
2:21:43 - Where to learn the mathematics for machine learning
2:22:23 - Books for machine learning
2:24:27 - Where to learn cloud services
2:24:47 - Helpful rules and tidbits of machine learning
2:26:05 - How and why you should create your own blog
2:28:29 - Example machine learning curriculums
2:30:19 - Useful machine learning websites to visit
2:30:59 - Open-source datasets
2:31:26 - How to learn how to learn
2:32:57 - PART 6: Summary & Next Steps

[casekingz]

This is by far the most visual map ever created for ML. Daniel is a genius. Energy, communication, value is the most I have ever experienced. Keep this up

[spartancass]

Daniel, thanks for this superb video. As someone just starting out on this road, it's very easy to get sucked into the fine details, but this has given me a much better grasp of the big picture. I love your philosophy of not learning for learning's sake, but using this knowledge to build things that matter to people. Keep doing what you're doing!

[jac]

I'm enjoying this so far. I just started using whimsical and I already love it!