louisfb01/start-machine-learning louisfb01/start-machine-learning

  • Stars
    star
    4,371
  • Rank 9,826 (Top 0.2 %)
  • Language
  • License
    MIT License
  • Created about 4 years ago
  • Updated 4 months ago
Twitter logo Share LinkedIn logo Share Facebook logo Share
louisfb01/start-machine-learning
github

louisfb01

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

A complete guide to start and improve in machine learning (ML), artificial intelligence (AI) in 2024 without ANY background in the field and stay up-to-date with the latest news and state-of-the-art techniques!

Start Machine Learning in 2023 - Become an expert for free!

A complete guide to start and improve in machine learning (ML), artificial intelligence (AI) in 2023 without ANY background in the field and stay up-to-date with the latest news and state-of-the-art techniques!

This guide is intended for anyone having zero or a small background in programming, maths, and machine learning. There is no specific order to follow, but a classic path would be from top to bottom. If you don't like reading books, skip it, if you don't want to follow an online course, you can skip it as well. There is not a single way to become a machine learning expert and with motivation, you can absolutely achieve it.

All resources listed here are free, except some online courses and books, which are certainly recommended for a better understanding, but it is definitely possible to become an expert without them, with a little more time spent on online readings, videos and practice. When it comes to paying courses, the links in this guide are affiliated links. Please, use them if you feel like following a course as it will support me. Thank you, and have fun learning! Remember, this is completely up to you and not necessary. I felt like it was useful to me and maybe useful to others as well.

Don't be afraid to repeat videos or learn from multiple sources. Repetition is the key of success to learning!

Maintainer: louisfb01, also active on YouTube and as a Podcaster if you want to see/hear more about AI!

Twitter

Feel free to message me any great resources to add to this repository on [email protected]

Tag me on Twitter @Whats_AI or LinkedIn @Louis (What's AI) Bouchard if you share the list!

Want to know what is this guide about? Watch this video:

👀 If you'd like to support my work, you can check to Sponsor this repository or support me on Patreon. You can also support me by following my favorite (free) daily AI newsletter to get frequent updates on new research and applications in AI!

Or support me by wearing cool merch!

Table of Contents

Start with short YouTube video introductions

Start with short YouTube videos introductions

This is the best way to start from nothing in my opinion. Here, I list a few of the best videos I found that will give you a great first introduction of the terms you need to know to get started in the field.

Another easy way to get started and keep learning is by listening to podcasts in your spare time. Driving to work, on the bus, or having trouble falling asleep? Listen to some AI podcasts to get used to the terms and patterns, and learn about the field through inspiring stories! I invite you to follow a few of the best I personally prefer, like Lex Fridman, Machine Learning Street Talk, and obviously, my podcast: What's AI by Louis Bouchard, where you will learn about incredibly talented people in the field with inspiring stories sharing the knowledge they worked so hard to gather.

Follow free online courses on YouTube

Follow free online courses on YouTube

Here is a list of awesome courses available on YouTube that you should definitely follow and are 100% free.

Read articles

Read many articles

Here is a list of awesome articles available online that you should definitely read and are 100% free. Medium is pretty much the best place to find great explanations, either on Towards AI or Towards Data Science publications. I also share my own articles there and I love using the platform. You can subscribe to Medium using my affiliated link here if this sounds interesting to you and if you'd like to support me at the same time!

Read Books

Read some books

Here are some great books to read for the people preferring the reading path.

Great books for building your math background:

A complete Calculus background:

These books are completely optional, but they will provide you a better understanding of the theory and even teach you some stuff about coding your neural networks!

No math background for ML? Check this out!

No math background for ML? Check this out!

Don't stress, just like most of the things in life, you can learn maths! Here are some great beginner and advanced resources to get into machine learning maths. I would suggest starting with these three very important concepts in machine learning (here are 3 awesome free courses available on Khan Academy):

Here are some great free books and videos that might help you learn in a more "structured approach":

If you still lack mathematical confidence, check out the Read books section above, where I shared many great books to build a strong mathematical background. You now have a very good math background for machine learning and you are ready to dive in deeper!

No coding background, no problem

No coding background, no problem

Here is a list of some great courses to learn the programming side of machine learning.

Check out the What's AI podcast for more AI content in the form of interviews with experts in the field! An invited AI expert and I will cover specific topics, sub-fields, and roles related to AI to teach and share knowledge from the people who worked hard to gather it.

Follow online courses

(Optional) Get a better understanding and more guided practice by following some online courses

If you prefer to be more guided and have clear steps to follow, these courses are the best ones to do.

For specific applications:

Get your models online and show them to the world:

Practice, practice, and practice!

Practice is key

The most important thing in programming is practice. And this applies to machine learning too. It can be hard to find a personal project to practice.

Fortunately, Kaggle exists. This website is full of free courses, tutorials and competitions. You can join competitions for free and just download their data, read about their problem and start coding and testing right away! You can even earn money from winning competitions and it is a great thing to have on your resume. This may be the best way to get experience while learning a lot and even earn money! Another great opportunity for projects is to follow courses that are oriented towards a specific application like the AI For trading course from Udacity.

You can also create teams for kaggle competition and learn with people! I suggest you join a community to find a team and learn with others, it is always better than alone. Check out the next section for that.

Want to build language models/apps? Check this out!

I had a lot of requests from people wanting to focus on natural language processing (NLP) (models dealing with language) or even learn machine learning strictly for NLP tasks. This is a section dedicated to that need. Happy NLP learning!

  • A complete roadmap to master NLP in 2022
  • Become an NLP pro with Coursera's Natural Language Processing Specialization by deeplearning.ai - Paid "Break into the NLP space. Master cutting-edge NLP techniques through four hands-on courses!"
  • An NLP Nano Degree! — Paid "Learn cutting-edge natural language processing techniques to process speech and analyze text. Build probabilistic and deep learning models, such as hidden Markov models and recurrent neural networks, to teach the computer to do tasks such as speech recognition, machine translation, and more!"
  • NLTK Book is the free resource to learn about fundamental theories behind NLP: https://www.nltk.org/book/
  • Looking to build a quick text classification model or word vectorizer, fasttext is a good library to quickly train up a model.
  • Huggingface is THE place to get modern day NLP models, and they also include a whole course about it.
  • SpaCy is great for NLP in production, as it does NLU, NER, and one can train classification, etc with it. It's also able to add customized steps or models into the pipeline.
  • Prompting! Prompting is a new skill that you should master if you want to build NLP-related apps. This is a great course I am contributing to, intending to teach prompting and give tips for specific models.

Twitter

More Resources

Join communities!

Save Cheat Sheets!

👀 If you'd like to support my work, you can check to Sponsor this repository or support me on Patreon. You can also support me by following my favorite (free) daily AI newsletter to get frequent updates on new research and applications in AI!

Or support me by wearing cool merch!

Follow the news in the field!

  • Subscribe to YouTube channels that share new papers - Stay up to date with the news in the field!

  • LinkedIn Groups

  • Facebook Groups

    • Artificial Intelligence & Deep Learning - The definitive and most active FB Group on A.I., Neural Networks and Deep Learning. All things new and interesting on the frontier of A.I. and Deep Learning. Neural networks will redefine what it means to be a smart machine in the years to come.
    • Deep learning - Nowadays society tends to be soft and automated evolving into the 4th industrial revolution, which consequently drives the constituents into the swirl of societal upheaval. To survive or take a lead one is supposed to be equipped with associated tools. Machine is becoming smarter and more intelligent. Machine learning is inescapable skill and it requires people to be familiar with. This group is for these people who are interest in the development of their talents to fit in.

  • Newsletters

  • Follow Medium accounts and publications

    • Towards Data Science - "Sharing concepts, ideas, and codes"
    • Towards AI - "The Best of Tech, Science, and Engineering."
    • OneZero - "The undercurrents of the future. A Medium publication about tech and science."
    • What's AI - "Hi, I am Louis (loo·ee, French pronunciation), from Montreal, Canada, also known as "What's AI". I try to share and explain artificial intelligence terms and news the best way I can for everyone. My goal is to demystify the AI “black box” for everyone and sensitize people about the risks of using it."

  • Check this complete GitHub guide to keep up with AI News

Find a machine learning job

  • Read this section from the article full of interview tips and how to prepare for them.
  • Learn how the interview process goes and getting better at preparing for them by watching how others did it, like the interview series I ran with experts from NVIDIA, Zoox (Self-driving company), D-ID (Generative AI Startup), etc.

AI Ethics

Tag me on Twitter @Whats_AI or LinkedIn @Louis (What's AI) Bouchard if you share the list!

👀 If you'd like to support my work, you can check to Sponsor this repository or support me on Patreon. You can also support me by following my favorite daily AI newsletter to get frequent updates on new papers like those!. Thank you, and let me know if I missed any good resources!

This guide is still regularly updated.

More Repositories

1

best_AI_papers_2022

A curated list of the latest breakthroughs in AI (in 2022) by release date with a clear video explanation, link to a more in-depth article, and code.
3,196
star
2

best_AI_papers_2021

A curated list of the latest breakthroughs in AI (in 2021) by release date with a clear video explanation, link to a more in-depth article, and code.
2,908
star
3

Best_AI_paper_2020

A curated list of the latest breakthroughs in AI by release date with a clear video explanation, link to a more in-depth article, and code
2,233
star
4

start-llms

A complete guide to start and improve your LLM skills in 2024 with little background in the field and stay up-to-date with the latest news and state-of-the-art techniques!
544
star
5

best_AI_papers_2023

A curated list of the latest breakthroughs in AI (in 2023) by release date with a clear video explanation, link to a more in-depth article, and code.
221
star
6

Top-10-Computer-Vision-Papers-2020

A list of the top 10 computer vision papers in 2020 with video demos, articles, code and paper reference.
190
star
7

top-10-cv-papers-2021

A curated list of the top 10 computer vision papers in 2021 with video demos, articles, code and paper reference.
126
star
8

iterative-grabcut

This algorithm uses a rectangle made by the user to identify the foreground item. Then, the user can edit to add or remove objects to the foreground. Then, it removes the background and makes it transparent.
Jupyter Notebook
44
star