Bifalgorithm post

This is exactly how I'd learn machine learning for free if I had to start all over again. You're pretty much insane if you don't start off with Python because almost every machine learning role uses that as its basics. To learn it, you can use the free CS50 course from Harvard or you can use Free Code Camp to get you fluent. The number one mistake that I see everyone do is that they spend three months learning a bunch of math like linear algebra that they don't need and they quit before they even start building their first model. So please do yourself a favor and don't do this. So just learn the math as you go and don't wait to finish it all because you never will use three blue one brown for any linear algebra. They're probably the best out there and then use can Academy for any calculus and for any stats or machine learning concepts use stat quests. Now for the actual machine learning core part you want to use scikit learn and learn the workflow. So you have split train and test test and you can learn stuff like linear regression, classification, tree models and cross validation. And you can use free resources like Andrew Nings machine learning specialization and also the hands on machine learning book. And now you want to use AI to practice. So you can ask AI to give you a challenge and you first want to build it out completely by yourself. After you've done this, you can ask AI to actually review your code and see exactly what you did wrong. I'd recommend Claw for this one because it's really good at picking out the specific flaws you made in the technical side. I also know that a lot of people don't like using AI for these kind of things, but it's 10 times better than just sitting down and watching a tutorial. After this, you want to just start building our project. So pick something that you're interested in and just build it out. It doesn't have to be something complex. Just make sure that you're passionate about it to make sure that you finish the project. And this is because one OK project is better than 10 projects that you haven't finished yet. Once you've completed the project, make sure to put on your GitHub, your LinkedIn, your resume. Just make sure to post it wherever you can so that recruiters can actually see what you built. And since you follow me, you probably know these already. But let me know what other machine learning content you want to see.

This is exactly how I'd learn machine learning for free if I had to start all over again. You're pretty much insane if you don't start off with Python because…

Ideas in this flowchart

  • Learning Machine Learning for Free
  • Start with Python
  • Free Resources for Python
  • CS50 Course from Harvard
  • Free Code Camp
  • Avoid Math Overload
  • Learn Math as Needed
  • Math Resources
  • Three Blue One Brown for Linear Algebra
  • Khan Academy for Calculus
  • Stat Quests for Stats & ML Concepts
  • Core Machine Learning
  • Use Scikit-Learn
  • Learn Workflow
  • Free ML Resources
  • Andrew Ng's ML Specialization
  • Hands-On Machine Learning Book
  • Practice with AI
  • AI Challenges
  • AI Code Review
  • Build a Project
  • Share Completed Projects
  • Platforms for Sharing
  • GitHub
  • LinkedIn
  • Resume
Feed/

This is exactly how I'd learn machine learning for free if I had to start all over again. You're pretty much insane if you don't start off with Python because almost every machine learning role uses that as its basics. To learn it, you can use the free CS50 course from Harvard or you can use Free Code Camp to get you fluent. The number one mistake that I see everyone do is that they spend three months learning a bunch of math like linear algebra that they don't need and they quit before they even start building their first model. So please do yourself a favor and don't do this. So just learn the math as you go and don't wait to finish it all because you never will use three blue one brown for any linear algebra. They're probably the best out there and then use can Academy for any calculus and for any stats or machine learning concepts use stat quests. Now for the actual machine learning core part you want to use scikit learn and learn the workflow. So you have split train and test test and you can learn stuff like linear regression, classification, tree models and cross validation. And you can use free resources like Andrew Nings machine learning specialization and also the hands on machine learning book. And now you want to use AI to practice. So you can ask AI to give you a challenge and you first want to build it out completely by yourself. After you've done this, you can ask AI to actually review your code and see exactly what you did wrong. I'd recommend Claw for this one because it's really good at picking out the specific flaws you made in the technical side. I also know that a lot of people don't like using AI for these kind of things, but it's 10 times better than just sitting down and watching a tutorial. After this, you want to just start building our project. So pick something that you're interested in and just build it out. It doesn't have to be something complex. Just make sure that you're passionate about it to make sure that you finish the project. And this is because one OK project is better than 10 projects that you haven't finished yet. Once you've completed the project, make sure to put on your GitHub, your LinkedIn, your resume. Just make sure to post it wherever you can so that recruiters can actually see what you built. And since you follow me, you probably know these already. But let me know what other machine learning content you want to see.

"This is exactly how I'd learn machine learning for free i"

👍
0
0 comments0 shares

Sign in to view and post comments.