Yep, I'm finally back Hey there everyone, Hitesh here, back again with another video I know you have been missing me a lot and I haven't made video in the last Two weeks or so of these camera types of videos I have been consistent making a Flexbox series But I was on a travel, and I could only afford making a screencasting videos on that, but regardless of that Finally I'm back, and today's topic is really interesting. I'm going to talk about machine learning What is machine learning in Layman's term and how you can get started in machine learning. A lot more is about to come. So let's get started! Now the terms – Machine learning and AI artificial intelligence is closely related And it's not wrong to say that the abstraction level of between these two words is fairly thin line and they can be Interchangeably used, but when I say machine learning or artificial intelligence, what most of the people saying is the same old terminator movie. You think that there is going to be some Tx 9000 machine that is going to come up from the future, is going to destroy entire humanity, you start panicking and And you will, you just think that there is not going to be any need of programmers in the future and a lot of theories like that? Hey hold down there ! This is not actually a fictional movie, if this could have been true so we should stop testing about with a Gamma-Rays because it can generate a Hulk and we should stop looking into the space because we may find aliens and that may invade into the earth. There might be a Thor coming up to save all of you and there might be a Spider man roaming around and who knows, there might be a Batman, too! So hold on your horses we need to talk a lot about machine learning and what actually it is. So putting down your terminator movie theory aside for a minute let's talk about machine learning and AI. Now machine learning and AI all these are branches of computer science with Almost who are doing their masters and Phd might have studied in their curriculum as well. They are closely related, but according to me, what my personal thought is machine learning is closely related to
data mining rather than AI. AI is completely a different thing But what you think of machine learning is closely related to data mining And you have been already using it quite a lot. Now, you might be asking hey where We are already using machine learning? Now although you have just heard the term machine learning But you might already be aware
of the term known as data mining. Now Data mining has been there since the evolution of data and computers which have been into the world quite a lot and all the things that you see. Simple examples would be Spam emails. You see that some of your emails are in your inbox and some of them are into Spam box. What is that? That is machine learning!
Rather closely that is Data mining. There is a huge chunk of data and your program and algorithm is designed in such a manner So that it can predict that whether this email is spam Or is it a good email that needs to be delivered in Inbox. Is it always perfect? No, not at all! Sometimes good email also land up in the spam and spam email ends up in the inbox. So that is basically a good example of machine learning, at a very small level. But now things are changing.
That was Version 1 of machine learning Now what we are seeing in our day to day life
is machine learning Version 2. So, how actually this is working all nowadays? So if I talk about the machine learning at a very broad scale There are a couple of components that you need to be worried about. First of all, is a huge data set. Data set
that can predict a lot of things, for example If I just show you a chair you can say hey, that's a chair! But if I say that that's a wooden chair,
that's a glass chair And there are tons of gazillion, bazillion type of chair; You can see the difference between all these chairs and can still predict that that's the chair. But if I just ask you to write a program for that, that could have been nightmare for you. For example If you're just writing a program that
it should have a four legs and some wooden texture That would be a chair. But what about when I say that -hey, it can be just a centralized table, having a central base and a glass sitting area That is also a chair, but you cannot write
a program for that and for such situation We require a huge number of Data sets. That's problem number one. The second thing that data set is being Pitched to something known as classifier. Which is again a big term, big big term but rather
I would say that is just an algorithm which can Determine the output based on whatever the Data is being fetched. And as we all know the more data We are going to have the more prediction capability is going to be there. So now based on what kind of data You are supplying, your classifier can classify The image or any other thing. In this example We are just taking an image of chair so it can predict that image of chair with some certain amount of confidence that it can be chair. It can never be 100% sure but it's always about the ratio of How much confidence that it's showing that ab
is that 99% chair? Is it 80% chair and is it 70 percent chair? So this is all on a broad scale what the machine learning is. What we are trying to teach with the machine and Yes, I know some of you are worried about, hey in the future It's going to be the AI and the machine learning are going to learn to write the code So there will be no need of programmer. Hold down your horses! Who told you that first of all? With the evolution things changes quite a lot I do agree But this is almost similar to the strike that I saw in my childhood, when people were opposing the computers. Everybody in the government department Private sector was saying that hey if computers will come up They will take our job. Did computers did that? Perhaps! But did it open more number of job as compared to that the job that is taken? For sure, it has done!
The same thing Is applied here. Is it going to take the job of programmers? Who knows ? But is it going to open up more more Responsibilities and more scenarios of working jobs? For sure it is going to be there! So on a whole note There is no such thing to be worried about that machine learning the future ismachine learning and AI
and we don't need Programmers in future. In fact
we do need more programmers in future. So now that you understand that how machine learning work on a simple scenario, a huge number of Data set being given to classifier and based on That data set, it just do some processing and
tries to predict the results. That's basically your machine learning,
being applied at a lot of places. Spamming is one of them. Recently, if you saw the google's new product, you can just open up
your camera app and can see the restaurants name and based on handwriting prediction image prediction and logo prediction it can query to the humongous amount of Data set that is present at the Google and can find out the ratings of the restaurants the name of the restaurants and some reviews about the restaurant. That's just one example of machine learning. Have you used some kind of app which predicts- How you will look like in your 80's or your 90's?
How your face is going to get at some deformation? Your skin is going to get some kind of deformation. This is all based on machine learning. Small level of examples, but yes, this is all based on machine learning! So now that on a very big scale you understand,
what is machine learning, How you can get started in machine learning? Now there are a couple of ways of getting started in machine learning and everybody has its own implementation of machine learning. Now let me walk you through how you can get started in learning machine learning. Now that is a vague thing learning machine learning. Okay So how you can get started with machine learning? Machine learning is first of all dependent quite a lot in math, but not all the time It's going to be like designing your neural networks or designing your patterns and all these things.
It's not all the time about that but based Example or base core setup of machine learning is dependent on that as well But the first language that you should be looking up in order to get started with machine learning is Python. Python being the very first language
for took advantage and brought us up the libraries
like scikit and Tensor flows. Obviously the language has its perks, And it is being heavily used in machine learning. Now before you get started and jump directly into the scikit and tensorflow Documentation and everything, let me tell you
that Python needs to be there in your pocket Nobody is going to teach you in a machine learning course that hey how to write a loop or
how to loop through an array Or how to define these set of lines into a function or create a new classes. These are all basics
that you should have Already in Python. Just onto a side bar here you can see the link for amazing Python course at an affordable rate Go ahead try that out. All I'm saying slide bar over now Let's come back here So Python is the one way of getting started with machine learning and most people think
that's the only way But that's not true. Most of the other languages are also coming up with the machine learning. But again depends on how much data set you are having or how much data you can collect? It's heavily dependent on that. Now other one language, which I will not call a language It's the company which came up with the implementation of machine learning
for public user is Apple. So if you got an Apple machine like Macbook or iMac or Mac mini you can get started in iOS 11.
Where just like we Used to have core data and avfoundation. We now have a new kit Ml Kit -which is machine learning . All you have to do is patch it a data set and it can produce a result.
It always just show You there what kind of input it is expecting and what kind of output it will give to you.
Very very easy to implement Recently in the bootcamp just a few days ago We created an app which you can just
take a photo of anything And it will predict what that object it will be.
It can be a light, a camera Remote control, a hot dog, a pizza We had a lot of fun playing around with that, in fact We spent almost half a day in playing it on with that app. So yes, Apple is trying hard so that everybody get an access to machine learning and everybody is able to design such apps. Possibilities with such kind of Ml Kit are endless And I can see a huge future there as well. Now one of the other thing that has impressed me a little bit not much is
Are they good? Not at all! Are they going to be good in future? For sure!
that it's going to perform really well So I would say yes it may come up in the future somehow or maybe some library does come out of the blue and we might get something amazing.
So right now Python and iOS 11 are the two good ways of
getting started in machine learning and
this is the condition right now in end of july 2017 Surely this is going to change up in near future So these were all the views about what basically
the machine learning is and how you can
get started with machine learning Was this an entire comprehensive thorough discussion about what is machine learning, classifiers, and tensors and scikit? Of course not, this was just an overview so that I can answer some of your questions And you can get some answers about machine learning and getting started and that. Is it a taboo? No Nothing is the taboo, anybody can learn machine learning programming or anything like that. Even if you are bad at math with practice you can become good in that. So that's all I'm saying here. So that's it for this video, and
I know you have missed me quite a lot I have missed you too guys as well But now the constant videos are going to come up because I'll be staying home for a few days more So that means a lot more videos and
don't forget to join me on Sunday live at every Sunday We do Sunday live and you can get the information about it on my Facebook page The Links are in the description as well as on the screen So that's it for this video, and I'll surely
catch you up in Sunday live !!