Humans are getting lazier day by day. We want our lives to be as easy as possible. For that purpose, we created machines — machines that are capable of understanding commands and performing tasks for us.
But what if machines could think and take decisions on their own? Sounds rubbish! But in this modern era of machines and technology, this is actually taking place. Big companies like Google and Facebook are actually doing these miracles!
Have you ever though about how, when you upload pictures on Facebook, the computer automatically detects faces and statistics suggesting your friend's name for tagging? Have you ever thought about how, while checking flights on Google for a particular destination, you start getting emails for flight-related offers?
At least once in your lifetime, you must have seen at least one Marvel movie, and you also must know that why these movies are so famous across the globe. Let's talk about Iron Man. This movie is so popular because it takes you to a virtual world where a machine can do such cool things. If you ask yourself how some of those things are happening, you'll come to the conclusion that there's a supercomputer actually doing all these things.
If a computer can make decisions by analyzing the facts, then it may be able to perform miracles.
All these facts amazed me, so I decided to start learning about the science of machine learning. But it was not easy, and it's very expensive to take beginner courses.
When you start searching for some material, you will find many algorithms, concepts, and books about machine learning that are very complex. And before starting these concepts, you also need plenty of math knowledge
So, I decided to write this blog. I will not give you names of heavy books or big-name algorithms, but instead, I'll give you the gist of all the things that you should know before you dive into machine learning world.
In calculus, you need some concept of differentiation — especially chain rule — and you also need integration. All these concepts will help you understand various algorithms that are using these concepts.
Probability Theory is a mathematical framework for representing uncertain statements. It provides a means of quantifying uncertainty and axioms for deriving new uncertain statements. In artificial intelligence applications, we use Probability Theory in two major ways:
- First, the laws of probability tell us how AI systems should reason, so we design our algorithms to compute or approximate various expressions derived using Probability Theory.
- Second, we can use probability and statistics to theoretically analyze the behavior of proposed AI systems.
In Probability Theory, starting from the basics, you have to cover some distributions like Bernoulli distribution, multinodular distribution, etc.
You also need some basic knowledge of permutations and combinations so that you can apply these concepts in probability and some algorithms as well.
After understanding the basics of these things, you should be able to jump into learning algorithms. These concepts will also help you understand the complexity of algorithms as well as build your own algorithms.
This blog is to list out a few small things that you must understand before you start learning machine learning itself. If you don't want to just use already-developed machine learning algorithms and you'd rather go in-depth so that you can learn the actual workings of those algorithms, then this blog is for you. In our next blogs, we will be going into the details of machine learning, with their implementations from beginner to advanced.