What is machine learning and how does it work

What is machine learning and how does it work?

What is machine learning and how does it work

Explain machine learning

Perhaps you've heard the word machine learn a lot in the past few years and today I just wanted to talk to you about what it actually means a lot of people think artificial intelligence and machine learning are the same things, but they're actually not artificial intelligence or artificial intelligence, as cute kids say, the field The whole thing is dedicated to making machine learning machine intelligent, it's a section of AI, and it's really cool because you don't really need to program the machine to do what you want to improve or learn by repeating the same task over and over again by switching the process a little bit every time until you do exactly what you want K What is similar to how a person learns from experience to give you an example of imagining that your grandfather works at the local level and his job is to sort apples from bananas but he suffers from bad pain and complains all the time so you want to program a device to do this task for him The first thing to do is to identify some features Can be used to distinguish apples from bananas

Its color may be more red, possibly a yellow apple or likely to be a banana, it is a very good starting point but what if we encounter a situation like this color is clearly not enough that we need another feature that there may be another good feature, the more it increases Its temperature, the more likely it is an apple, the more likely it will be a banana, we can choose a lot of features but let's keep it two simple things now that we have identified some features that we need to collect some data to train our devices until you go and get 50 apples and 50 Bananas and classify each as 1 item 2 along a For a path up to 100 then you measure the color and difficulty of every single note, whether it is an apple or banana and enter your data in the device. Now it is time to initially test some kind of sucks even though it has two features of color and hardness that does not know how important or as computer science en He says that waiting until you put on each one of them the idea of ​​weights in decision making may be the central idea in machine learning and this is something we are all familiar with saying we are looking for a romantic partner and two things you were looking for our intelligence and a nice smile but maybe you put more weight on your intelligence than You do a nice smile

But also if they don't smile, it won't be good either. Still playing some weight on a gentle smile plays a huge role in any decision and that's why when your friend tells you that you have found your good match, they are always wrong, they may know the features they like But they do not know the weights that separate machine learning from previous forms of artificial intelligence is its ability to know these weights that you make by comparing its results with the data you gave them at the beginning Your fruit sorting machine randomly distributes the weight starting with element 1 which will include very pens For Elmo Very unripe which is of course much more difficult than regular bananas if it weighs a lot more on hardness, it will be okay, so it should be an apple but by comparing that to the data you provided on element 1, he will realize that he made a mistake, adjusting it so that it is placed Less weight on hardness and more weight is placed on the color but it skips and when it encounters Apple if it is yellowish, it classifies it as a banana but again by comparing its results with respect to the data you provided, you realize that it is wrong and you reset the weights again

And repeat this process of comparison and pre-amendment so that you hardly make any mistakes after some time ready to take over your grandfather's job in the local market. This example was a simplified version of what Facebook does when it distinguishes you in an image Facebook has learned your face by analyzing images that you know measure the size of your eyes or the length of your nose and uses this data to determine I suspect that you are in the next image, in fact, machines get a good atmosphere in general 2015, where a robot first overcame human and image recognition, and now they are developing robots that can clean your house for you, how wonderful if you want to learn more about how this weight control process works