No matter how much programming and debugging you might know, if you don’t know your basics, you can still end up being rejected by a company. Why? Well, you can’t build a house without laying the foundation, right?
It’s okay if you are new and you don’t know the necessary definitions, or if you get confused and mix them all up. In fact, there aren’t any actual ‘definitions’, per se. Most of these are just concepts that experts, leaders, and random people on the internet have ‘defined’ in their own words. So let’s take a look at these concepts and their relation with one another in this simple little cheat sheet -
It is the collection, preparation, and analysis of data, in order to gain some information from it, with the help of many different tools and techniques.
Artificial Intelligence (AI):
It deals with giving machines the ability to think and behave like a human being.
Machine Learning (ML):
It is the process of training machines to perform a particular task, without any explicit programming.
Deep Learning (DL):
It is a part of Machine Learning that involves the use of Neural Networks, in order to replicate the human brain.
Let us now take a look at their relation with one another. Here is one important thing to remember:
DL is a subset of ML, which is a subset of AI, which uses Data Science.
Many people get confused by this concept, but it’s simple really.
- As shown in the diagram, there is an intersection between AI (which includes ML and DL) and Data Science, but neither is a subset of the other.
- AI is not a subset of Data Science, however, it uses Data Science techniques to carry out its tasks.
- Since ML and DL come under AI, they require Data Science techniques as well.
So from a definition perspective, this is all you need to know. Once you get comfortable with these ideas, you will be able to explain it with ease when questioned during an interview, and that will make you appear more confident, thus giving you better results during your job search.