Saurav Jain (Open Source + Communities) Profile picture
Developer Community Manager @Apify โ€ข ex ๐Ÿฅ‘@amplication โ€ขOpen Sourceโ€ข Web Scraping/Automation โ€ข AI โ€ข Python โ€ข JavaScript โ€ขGitHub โ€ข Node.js

Jul 6, 2021, 9 tweets

๐—œ๐—ป๐˜๐—ฟ๐—ผ ๐˜๐—ผ ๐— ๐—ฎ๐—ฐ๐—ต๐—ถ๐—ป๐—ฒ ๐—Ÿ๐—ฒ๐—ฎ๐—ฟ๐—ป๐—ถ๐—ป๐—ด ๐Ÿ’ก

Let me introduce you to the absolute starting of Machine Learning

-What is ML?
-Its types
-Some real-world applications

๐—ช๐—ต๐—ฎ๐˜ ๐—ถ๐˜€ ๐— ๐—Ÿ? ๐Ÿ’ป

I have said this earlier too that I have done various ML courses but one of the best definition is from Andrew Ng course-

"Machine learning is the science of getting computers to act without being explicitly programmed."

๐—ง๐˜†๐—ฝ๐—ฒ๐˜€ ๐—ผ๐—ณ ๐— ๐—ฎ๐—ฐ๐—ต๐—ถ๐—ป๐—ฒ ๐—Ÿ๐—ฒ๐—ฎ๐—ฟ๐—ป๐—ถ๐—ป๐—ด

-Supervised
-Unsupervised
-Reinforcement
-Semi-supervised

๐—ฆ๐˜‚๐—ฝ๐—ฒ๐—ฟ๐˜ƒ๐—ถ๐˜€๐—ฒ๐—ฑ ๐—Ÿ๐—ฒ๐—ฎ๐—ฟ๐—ป๐—ถ๐—ป๐—ด ๐Ÿ’ฌ

If the input is square, triangle, and hexagon.

We trained the model that -
4 sides = square
3 sides = triangle
6 sides = hexagon

and when we test on new data it already knows how to predict and it does on basis of number of sides.

๐—จ๐—ป๐˜€๐˜‚๐—ฝ๐—ฒ๐—ฟ๐˜ƒ๐—ถ๐˜€๐—ฒ๐—ฑ ๐—Ÿ๐—ฒ๐—ฎ๐—ฟ๐—ป๐—ถ๐—ป๐—ด ๐Ÿ“ˆ

Here we do not classify/label data.

For example, if watermelon and apple are mixed together.

Algorithm will create two clusters and learn from data itself that apple is small red and watermelon is big green etc.

๐—ฅ๐—ฒ๐—ถ๐—ป๐—ณ๐—ผ๐—ฟ๐—ฐ๐—ฒ๐—บ๐—ฒ๐—ป๐˜ ๐—Ÿ๐—ฒ๐—ฎ๐—ฟ๐—ป๐—ถ๐—ป๐—ด ๐Ÿค–

The concept of RL is so simple.

It is basically like training your pet to do tricks.

If it does it correctly you reward otherwise you punish and on the basis of feedback from the environment, it learns.

๐—ฆ๐—ฒ๐—บ๐—ถ-๐˜€๐˜‚๐—ฝ๐—ฒ๐—ฟ๐˜ƒ๐—ถ๐˜€๐—ฒ๐—ฑ ๐—Ÿ๐—ฒ๐—ฎ๐—ฟ๐—ป๐—ถ๐—ป๐—ด ๐Ÿ”Ž

In the real world, there are many datasets that are neither completely labeled nor completely unlabeled.

Therefore both supervised and unsupervised learning are not the best training methods here.

S-S works on both.

๐—ฅ๐—ฒ๐—ฎ๐—น-๐—ช๐—ผ๐—ฟ๐—น๐—ฑ ๐—”๐—ฝ๐—ฝ๐—น๐—ถ๐—ฐ๐—ฎ๐˜๐—ถ๐—ผ๐—ป๐˜€ ๐—ผ๐—ณ ๐— ๐—Ÿ โœ…

-Voice Assistants (Alexa, Siri, etc)
-Virtual Chatbots(Zomato, swiggy, amazon Customer Care complaint)
-Tesla Driverless Car
-Weather Prediction
-Netflix Movie Recommendation

Hey all, hope you all are learning something new from my threads.

I daily post threads about ML, Python, etc.

If you like my content, give retweet to the first tweet of the thread :)

Thanks !!

Share this Scrolly Tale with your friends.

A Scrolly Tale is a new way to read Twitter threads with a more visually immersive experience.
Discover more beautiful Scrolly Tales like this.

Keep scrolling