**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!
Came across this roadmap back in 2020 when i was joining University, bookmarked it and never looked back. Moved on to WebDev, CV and Leetcoding. Now in 2024: regretting that decision to not explore/learn ML. I'm finally starting ML and came back to this vid just to see it gettting updated for 2024.
the rising of chat gpt makes me want to get deeper into LLM, especially the ones from scratch, now im currently learning ur 25H tutorial on PyTorch, but planning it to watch until i am ready to step into LLM,
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.
@@ayaan3429 Hi, could you let me know if we have to go through these resources just in the order he mentioned it? Like ML problems first and ML Process next and so on?
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!
I've never left a comment on RU-vid, 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.
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!
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
"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
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.
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!
Daniel, this is an amazing video. I came back to say thank you for putting extensive work to make this video. The map, instructions, and resources are super helpful. This is the best guidance I have seen so far! Thank You Daniel
WOW!!!! Thank you for the incredible amount of work you put into this project, it is truly an amazing creation!! Very useful and relative information and the interactive map is really cool! Stupendous!
for intermediate level machine learning practitioners this an excellent reminder, a detailed machine learning landscape. Very huge contribution to the community. you did an Excellent job Daniel. Wish you the best
What a valuable resource ~ thanks for taking time to produce this, Daniel. I watched David Malon’s Harvard online CS 50 & 100 and wondered where that guy was when I was in high school ~ you both create engaging content. There are a lot of people who appreciate what you do.
Best descriptive material în one shot out there. And in simple human language. And the roadmap is just what many of us need to understand the big picture and not get lost in different aspecte. Learning those things is like walking through a labyrinth.
Great work Dan 👍🏽 , My learning path almost aligns completely, One thing i feel is missing is "Joining a local community of ML enthusiasts around".. it can be a lot more difficult being a lone ranger.
Thank you Daniel for putting together such an awesome roadmap! It helped me connect all the dots. As you said, there are so many resources out there on the internet but the challenge is to come up with the right path to achieve the goal. I was so confused until I saw this video. I think I have a lot more clarity now. Thank you once again.
Best roadmap for any AI/ML aspirants! . Thank you Daniel for such a comprehensive explanation full of valuable information complemented with inspiration and encouragement.
Thank you Daniel, 😊 This is the best movie I have seen in my life , now I have enough energy to boostup.⚡🔥 learnt a lot. It cleared all my queries.😇 I really love your setup.😁
Me checking the phone during a Pomodoro break: 'Oh, Dan uploaded a video.' I click it. Dan: "...I'm not going to hold you up for long. ..." - I look at the duration of the video. Me: Oh no...
Lol, man, You. Are. Amazing. Just thank you so much. I'm a software engineer and I don't know any ML engineers in person. It is so helpful to get something like this from the man from ML industry. So many thanks.
I've been self-studying full-time since January. Had to make my own curriculum and everything. Really interested to see how our roadmap and resources line up.
One of the viewers reached out to me via email so I thought I'd share it here for anyone else that was curious. This is copied from my email to him so it's LONG. I mainly used textbooks and Stanford/MIT lectures and coursework freely available on RU-vid and the courses' websites. I guess the biggest insight I learned from self-studying and everything is that the field is developing rapidly. It's getting easier and easier to access certain aspects of ML/DL without necessarily needing a deep understanding of the theory and academics to start working with them. This isn't to say that the foundations aren't important, but that you should actually start getting some hands-on experience sooner than you might think. If I was to distill the curriculum I had and maybe do things over from scratch I'd probably take the following approach. Start with basic probability and statistics on Khan Academy and the Statistics and Machine Learning playlists by StatQuest on RU-vid. Use python to recreate what you can during those courses (combinatorics, probabilities, mean, standard deviation, etc). Look for standard library tools that can do it as well! Like sampling in the standard library's random module (this came up in a coding interview and I tried to hand-code something that could've been solved in one line!). Learn to clean data. Numerical, categorical, timedate, EVERYTHING! (Datetimes ate up 2 out of 3 hours I was giving for another coding interview). Learn how to do a couple basic linear and nonlinear ML models with sklearn (single and multinomial linear regression, random forests, gradient boosting, svm). Add in a video or two on regularization (StatQuest has some I think). Make a couple models or so on jupyter notebook. Get comfortable with the commands and cleaning and try it out on a problem you're interested. Pick a random dataset and see what it's like to really clean it and have to form a pipeline to feed your model. The modeling is the easy part. If you're comfortable or bored, go to the Deep Learning for Coders course by FastAI. Jeremy Howard's videos are great and you can immediately start fiddling with things. He also has a free book (FastAI Book) which covers a lot of topics and goes alongside the course. My favorite part is that the course has a section on how to actually deploy these things and not let them die in a forgotten jupyter notebook somewhere. The truth of the matter is that the majority of the people will not be developing state of the art algorithms or libraries. The FastAI course will kinda show you that. Think of something that interests you, something connected to a hobby or thought. If you get interested in learning deeper theory on Machine Learning, check out Intro to Statistical Learning with Tibshirani, Hastie, and Witten. For Deep Learning, find Karpathy's CS231n series on youtube then watch the updated version of the course in high speed to find what advances have happened in the last couple years. A very dry but amazing book is Hands-On ML. The first two chapters alone cleared up so much for me as far as how a real project is structured. Extra: Learn FastAPI, streamlit and plotly/dash and start cranking out some webapps.
I am setting out on my path towards becoming a Machine Learning Engineer. I plan to devote 4 hours everyday and religiously hold this video as my compass everyday and find direction through all the clutter out on the web. Thank you so much!
you explain things exactly the way i think, sound like in explaining this stuff to myself. i also realise why people lose me when i'm explaining things to the haha. but nah i got what you would putting down and loved the professionalism of this video. That food example in the beginning is an amazing way to explain ML
I've just started to investigate ML as I'm a project manager, not a coder. So this introduction was the best I've seen so far, and I've been looking around for weeks. I particularly applaud the emphasis on being a chef, not a chemist. If you want a student to really get into a subject, you should start by having them fall in love with the subject, not begin at the molecular level. Your enthusiasm and clarity throughout this presentation supported that chef metaphor wonderfully. The only thing I would be interested in hearing your thoughts on are possible "fun" projects for beginners. I am not particularly interested in computer vision, for example, but using ML to create a custom audio engine, or ML to track personal bio-metrics, or something like that. I would love to know your ideas on some fun, easy projects. Thanks again for the wonderful work.
Hey, you are awesome, you have given so much of (WELL ORGANISED) content to everyone..... Great!!! I was wondering if you can make a similar one for Deep Learning??? Eager for it.
Thank you so much Jeet! There’s a fair bit of deep learning in this one, but if you’re looking for a dedicated deep learning one, I’d check out: github.com/dformoso/deeplearning-mindmap (these are what I originally based the roadmap on)
This is service to the society. Giving back to the community. One of the reason I love Software community is that lots of people give back to the community by creating amazing path(like this one),create open-source software and books and etc. Wish you the best
I have come up with a Life Goal of verifying everything so I can not be lied to anymore. That project is so vast that the Table Of Contents has become huge. I REQUIRE this kind of information to organize and make my research available to the world. I literally couldn't do it without this materia!!! Your enthusiasm sounds intimately familiar 😁😁😁 I set a goal of reporting in 35 years. This will enable my books/website material. I will have fun getting down to a 3 minutes summary in English. 15 languages total, for less than 1 hour of talking. This material will end all the lies that I have functioned under. Now how to structure my data. Cosmology should be interesting area to START! Electric Universe vs gravity only models for fun and profit👍🏻👍🏻👍🏻😁
Awesome, i was getting confused a lot when ever i thought to start machine learning, but one video by you cleared all my doubts and confusion in one shot
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. However, you might notice a few changes to the websites mentioned throughout video (some have had a design change), including sites like Made with ML who've recently pivoted: madewithml.com/pivot/ 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!
Sat through this beast (at 1.25x speed; perfect pace & Aussie accent). Gave me lots of clarity as I learn better from building than from watching videos. Guess I won't be needing Coursera Plus (yet)! Thanks so much Daniel!
I'm an undergrad still learning about the space and this video got me so excited to explore. I watched the whole video front to back and I cannot wait to see where my curiosity leads me!
holllyyyy shit the fact that this video is free and the accompanying resources are free is absolutely amazing. As an 18-year-old considering work in the field thank you so much for this content!!
Wouldn't miss a single update from this channel. Daniel has been a brilliant instructor for me in his Complete ML and DS course (which I would highly recommend to the newcomers)
Even though you posted this ages ago - just want to say THANK YOU SO MUCH for this resource, i've watched and clicked different bits at different times and it's literally always the ML and life boost I need haha !
Of all ML-related videos I've watched so far on youtube: This one is definitely the best. Particularly I like that you also mention other resources available for learning, in which you or your other colleague are not involved in. Makes you seem like a really nice guy. Greetings from Germany
You are a God send! I am a cs Third year student and had NO IDEA on how to get into ML as a career path. There’s so many resources if you want to be a software engineer, but barely any if you want to get into specifically ML engineering. Thank you so much for this mindmap thing. Cheers
It's like a world map in a classic RPG game! As a M.Sc student in AI I want to thank you for this AMAZING work! I'll use it as a daily basis for my projects!
I've been considering myself as a legendary procrastinator before watching this video. didn't even pause once, watched till the end. the most detailed guide, really, appreciate that
