Machine Learning is a buzzword amongst technology enthusiasts these days, but what exactly does it mean?
Let me explain it with a simple example, a Netflix recommendation. Now, that is simple, but not much informative, is it? No worries.
Let’s see what a Netflix recommendation has to do with ML. When you watch certain movie on Netflix, it recommends you other movie or series of similar genre. That means, it now knows what kind of movies you like. A software knows your preferences. That is exactly what ML is. You are teaching a machine or a machine is learning from you.
In simple programming, what you do is provide input and a formula to your code and it gives you an output, while in ML you provide input and output and in turn get a relation between them.
A much formal definition given by Tom Mitchell is
A Program is said to learn from Experience E with some tasks T and performance measure P, if it’s performance in T, as measured by P improves with E.
Informally, ML means ability to learn without being explicitly programmed.
This was all about meaning of Machine Learning. Let’s talk technical now.
As a developer, at some point of your career you would definitely come across some problem which cannot be solved by regular if-else statements.
For example, in a game of Tic-Tac-Toe, there are way too many combinations for it to be written successfully.
To solve these problems, you’ll be using ML algorithms.
I tried to write tic tac toe with regular if else statements, it is not efficient at all. You all can have a look at it if you want to.Install the apk and try it out.
That’s it for introduction.
Three paradigms of Machine Learning are:
· Supervised Learning.
· Unsupervised Learning.
· Reinforcement Learning.
We will be learning these in detail in following blogs.
Hope you enjoyed!
Machine Learning 