Why it took me 2 years to get started with machine learning when I could've done it in less than a month.

🧵👇
My first attempt of getting into machine learning was in early 2018.

I saw a few videos on YouTube but never really understood anything about it.

(2 / 10)
Terms like "Support Vector machines", "generative adversarial networks" always scared me.

Moreover there was nobody to guide me in the right direction.

(3 / 10)
I knew python decently well, however I always thought you need to know complex math which you could only get in college degree.

I dismissed the idea that I could get into machine learning before I got into college.

(4 / 10)
I learnt a bit of React, Vue and Flask in the meanwhile. I liked it however I knew it was something which I wasn't really interested in. I even tried to get into Game development and failed miserably at it!

(5 / 10)
In short, I was unclear as to what I wanted to do.

I lacked focus and consistency.

Being consistent is VERY important, you must focus on one thing and do the best you can at it.

(6 / 10)
In 2020, I finally got started with machine learning, I decided I am going to be more consistent with it and slowly I realised that this is what I am passionate about!

(7 / 10)
I made the mistake of listening to other people who themselves had no knowledge about this field and the second mistake was of not having clear direction on what I really wanted to do.

(8 / 10)
These some tips for machine leaning newbies.

1. You don't need math to "get started" machine learning
2. Learn Python (or whichever language you prefer) very very very well!
3. Practice
4. Have a clear path
5. Google things when you don't understand something

(9 / 10)
6. You don't need expensive hardware for machine learning
7. Understand what different frameworks do and use the ones you need.
8. Have confidence!

(10 / 10)
Congrats! You've read the entire thread 🤩

It takes me a lot of effort to make this kind of content and your support keeps me going.

Thank you!
You can follow @PrasoonPratham.
Tip: mention @twtextapp on a Twitter thread with the keyword “unroll” to get a link to it.

Latest Threads Unrolled:

By continuing to use the site, you are consenting to the use of cookies as explained in our Cookie Policy to improve your experience.