AI VS ML VS DL VS Data Science |

I'm going to clear a confusion and I'm going to tell you what exactly is artificial intelligence what exactly is machine learning what exactly is deep learning and how do we use data science considering all this particular technology and work so let us go ahead and let us just think I'm also going to create some. Venn diagrams so let me consider that this is my

**Venn diagram of AI**and the main work of AI you have heard of AI applications you have heard of a engineer slow kind of positions so AI basically helps us to it enables the computer or machine it enables the machine to think it enables the machine to think that basically means without any human intervention the machine will be able to take its own decision and always remember guys whatever .I am talking about over here with respect to AI right this is the final goal you are basically creating an AI application a self-driving car that is an

**.App which actually uses machine learning and deep learning within them is basically an AI application it does some kind of task so finally this is my final goal I have to reach over here and create an**

*AI application***okay now when I talk about machine learning machine learning is a subset .**

*AI app*### AI VS ML VS DL VS Data Science

**AI**okay so machine learning is a subset of AI and what does machine learning help us to do it provides us statistical tools statistical tools to explore the data to explore the data simple definition guys it provides us some statistical tools to explore and understand about that particular data now when. I talk about machine learning in machine learning you have three different approaches one is supervised machine learning. I'll also discuss about what exactly supervised okay so the second technique is something called as unsupervised machine learning the third technique is something called as reinforcement reinforcement learning or this is also called as semi-supervised machine learning okay .I can write it as semi-supervised so this techniques of machine learning is basically ranging in this let me give you a very good example of supervised so in case of supervised we'll be having some label data you know some passed data and with the help of this kind of data we'll be actually able to do the prediction for the future let me just take a very good example suppose based on I have two features in my data set like age I have I have not age let me just consider that I have height and weight as my two features .

I want to classify whether that person will is belonging to an obese category or whether it belongs to the fit category right so this kind of data initially whenever I'm making my model at that time. I'll have this day time and previously only and what I will do I'll create a model train on that data and with the help of those kind of data. I'll be actually creating a supervised machine learning model that basically means in case of supervised we have passed data passed labeled data okay we know what will be the output of this particular data now in the second category when I talk about unsupervised machine learning here. I'll not be having any labeled data that basically means in my data set I will not know what is the output so in unsupervised machine learning we usually solve clustering planet of problems clustering you know there are different different clustering techniques like k-means clustering

**so in answer machine learning we will actually be solving clustering techniques and when. I say clustering what exactly it does is that based on the similarity of that data it will try to group that data together and there is some mathematical concepts like euclidean distance actually used inside that width apart weights . Some other techniques also so most probably here are two different algorithms or three different decorative algorithms one is k-means clustering higher it'll mean clustering DB scan clustering these are the three popular clustering algorithms that we basically used in unsupervised machine learning now in case of reinforcement learning what will happen is that some part of your data will be labeled and later on .**

__hydrocal min clusterings__Some part of the data will not be labeled so the computer or the machine learning model learn slowly by seeing the past data and it will be learning as soon as the new environment new new data will be coming up so I hope you understood this that is what we are actually doing over here the most important part is that we need to have data it also it also provides some statistical tools to analyze explore and analyze the data okay and this is the three different techniques that we basically have in machine learning the last the third part which is my deep learning is again a subset of machine learning now why did deep learning good got created you know so what scientists thought is that can we make the Machine learn like how we with the help of human brain actually try to learn things you know that was a main idea behind deep learning.

### AI VS ML VS DL

so over here in deep learning you create architecture which is called as multi neural network architecture multi neural network architecture so at the end of the day we are basically using multi neural network architecture and we are actually creating some deep learning neural networks the main idea behind deep learning is to mimic human brain you know how human actually learns those concepts similarly we are creating models over here which is learning those things and the most important thing is multi neural network architecture right and in deep learning also you have various techniques one is and that is artificial neural network the second one is CNN that is convolution neural network and the third one is

**which is called as a weaker and neural network most of the problem statements most of the data which is actually present in the form of numbers will be solved with the help of a NN you know artificial neural network.**

__RNN__Suppose our input is in the form of images we will basically use CN n that is convolution neural network and suppose if our input is in the form of tiny series kind of data at that time we will be using recurrent neural network apart from this there are also techniques like transfer learning you know there's some advanced neural networks extension of the

**n so suppose if I take an example of mass 2 r CN n right so these are some advanced neural network architecture which where the base is actually a CN , architecture so you should try to understand this first of all I am actually using this concepts of machine learning and deep learning and the main goal is to derive an AI application you know by using this particular techniques.**

*CN n + 1 CN*I want to I want to create a model which will be I want to create a self-driving car so that is self-driving track maybe in our AIII application ok now the question arises where does data science fit into this right now data science is a technique which try to apply all this particular part means all these techniques that is basically machine learning deep learning now apart from that it also uses some tools some some some mathematical tools like statistics you know probability linear algebra linear algebra a whole lot of different different maths like differential calculus and all right and that is what this is basically my TS that is data science so a data scientist will have to work on

**based on the type of use case by using some mathematical tools like statistics probability linear algebra and many more ok and he may work in this three kind of machine learning he may work in this three kind of deep learning techniques right and this is the basic difference between an AI .AM L Hanan data science you have whole lot of these things that you basically learn when you want to become a data scientist isn't it amazing right because I have actually walked in each and everything each and every part of this all the techniques that.**

*M LDL*I have actually written down over here I've created some very good AI application some of the recommendation system supercool recommendation systems I have actually created you know and if I go and use this

**RNN**I've actually worked on time-series sales data with the help of RN in architecture I have extensively worked on

**CNN**'s you know where my inputs are in the form of images live feeds you know videos and all this particular technique so yes this was all about this particular video I hope you understood this particular video that we discussed that what is the basic difference between a I am

**data science please do subscribe the channel if you have not already subscribed and please share with all your friends.**

*LDL*If You like this article on

**AI VS ML VS DL VS Data Science Full Explained**then please give your comment below.

## 1 Comments

Thanks for the well-written post and I will follow your updates regularly.

ReplyDeleteMachine Learning course in Chennai

Machine Learning Training in Chennai

RPA Training in Chennai

RPA course in Chennai

Blue Prism Training in Chennai

Blue Prism Training Chennai

Automation Anywhere Training in Chennai

UiPath Training in Chennai

Machine Learning Training in Velachery