The Artificial Intelligence, Machine Learning Roadmap: How do I Learn Machine Learning?

Letters to Enthusiast

Dear Enthusiast,

If you are reading this letter, then you must have heard so much about Artificial Intelligence and Machine Learning. You must be asking the same question I was asking months ago, “…but how do I learn Machine Learning?”

In this article, I present to you clear guidelines on how to transition into this field. But there is only one rule in this game:

Rule number one:

Enjoy yourself at this step!

Surprised? Yeah that’s the rule. You must enjoy yourself at this step. At every step, you have to enjoy it.

If you are ready to keep to the rule, then let’s dive in.

Excited?

I am!

Step 1: Make up your mind

This is the first and most important step.

Heads-up…

You might feel overwhelmed at some point but if your mind is made up, you’d be able to go through and put all necessary efforts to move to the next step.

Remember the rule.

Step 2: Learn Python

In case you have forgotten, the rule says: Enjoy yourself at this step!

Python is a programming language that is easy to learn. Writing lines of codes is like giving directions to someone.

If you have never written a single line of code before, that’s fine. There is always a first time!

There are excellent resources out there that can help you from articles to videos. It depends on how you like to learn.

But how do I know what to learn?

You really need a structured course so that you don’t move randomly.

Check out freeCodeCamp or Programming with Mosh if you like videos.

If you like to read, you can learn from the python documentation here.

PS: that’s how I learnt as well.

DataCamp, tutorialspoint, medium, etc, also have great resources.

Disclaimer: Don’t expect to learn everything before you move on to step three. Once you can read a line of code and have a fair idea of what it does, you can move on to step three.

Really, if you devote time, after some weeks of learning python, you are ready to dive into step three.

Not to forget…

It would be very helpful to try your hands on coding projects and give yourself some challenging tasks on hackerrank, leetcode or similar sites.

Step 3: Start Machine Learning right away!

Remember the rule!

Yes, you heard me right. Start right away. There is no need to waste any time. You might have heard that you need math, but math can wait. If you can use a calculator, then you are fine.

As you begin this step, don’t think you would understand everything right away. Just learn the basics. As you progress, there woud be those aha moments when what you had learnt in the past comes to the surface and then you immediately understand it.

Again, you need guidance. You need a structured course!

Kaggle has an excellent resource. You can access it here. Once you are done with the introduction, you could level up to the intermediary level.

If you like videos, you can check up Coursera, Udemy, Udacity. They also have excellent, well structured courses on the introduction to Machine Learning. Personally, I learnt so much from Coursera, specifically Andrew Ng’s videos. But if you don’t have access to them, you can always learn on YouTube. Edureka, Programming with Mosh, have structured courses. Simply go on YouTube and dive right in.

I’m sure you’d feel great when you successfully run a project from start to finish. That’s how I also felt the first time. I was so excited!

I’d also encourage you to participate in Machine Learning competitions. They will help you in no small way. If you feel that you know nothing, welcome on board! I also felt that way. Should I tell you my little secret?

Bring your ears closer so that I can whisper. This is only beween you and I, promise? I trust you’d tell no one… not even Mama.

In a hushed voice…

I registered for my first competition with a name no one can trace to me!

Yeah, it was that bad. I felt I knew nothing and didn’t want everyone to know about it.

But you know what?

Things are very different now.

Again, don’t sweat it if you find yourself forgetting what you’ve learnt before or having to check up other people’s codes. Everybody faced the same problem. But if you remain consistent at learning, you’d find yourself writing your own codes!

Step 4: Learn some statistical and linear algebra basics

Now, you really must remember the rule. Enjoy this step!

Yeah. Some people would say this should be step three. Really, if you can, carry on with step three and four concurrently. But if you’re like me, you are very curious so you start machine learning before going into any stats or algebra.

For algebra, I absolutely love Kimberly Brehm. I was glued to her channel when I was learning algebra. She also has videos on statistics.

My stats favourite is Justin Zeltzer. He is excellent at giving intuitions. From probability to regression, you will have all you need.

Remember that there are also structured courses on Coursera, Udemy, Udacity on both statistics and linear algebra.

Step 5: Explore!

If you have followed through steps one to four, then you are set for exploration.

The ideas coming to your head aren’t crazy. If you can think it, there is a high chance it can be done.

Let’s call it a day today.

See you soon…

Your favourite ML blogger,

Success Vera