Hey Grandma what is it???

I hope that after reading this article the concepts AI and machine learning will be clear for you.

I will start explaining AI, but the focus of this article is talking about machine learning, as my grandmother used to tell me, you have to know how to walk before you start running........ So here we go!!!

Artificial Intelligence(AI) is the intelligence demonstrated by machines, WHAAAAAAT???, Since when machines have intelligence?? I know you may be thinking about famous movies when robots fight with the humanity. but no, when I said that the machines demonstrate intelligence, is because a lot of machines with AI are usually common in our lives, like the cellphone or TERMINATOR, the only difference between the intelligence of the above examples is that the cellphone have Weak AI that is artificial intelligence that is focused on one narrow task and Terminator have Strong AI that is a machine that exhibits behavior at least as skillful and flexible as humans do.

The main concepts of Artificial Intelligence are:

Machine learning

Is the study of algorithms that computers use the perform a specific task without using explicit instructions. That means that we no longer need umpa lumpas at the other side of our computers answering all the task we do. Machine learning is training a computer like training a dog leading him every morning to the street to pee, to the point that the dog predicts and goes alone. So with computers is the same is to train a computer with many examples, so it can predict new samples. Is like when you are looking for something in ebay and it starting to appear a lot of announce about this thing in facebook (Someone watches us).

Machine Learning have a subset that is Deep Learning this is used or computer vision, speech recognition, natural language processing and more amazing things.

Artificial Neural Networks

ANN are computing systems vaguely inspired by the biological neural networks that constitute animal brains, we will understand this a little bit more later.

Natural Language Processing

Is the technology used to aid computers to understand the human’s natural language. It is not an easy task to teach the machines to understand how we communicate, it is even a difficult task to explain what Machine Learning is but we are in that :)

Image Processing

It is a method to perform some operations on an image, in order to obtain an improved image or extract useful information from it. It is like a jealous couple that will review your photos in order to extract valuable information that will serve to start a problem.

Others:

Pattern Recognition, some Data Science algorithms, bit chain and more.

Go back again.......

The really important thing is to return to our initial topic in order to reach our goal, then knowing the difference between TERMINATOR and your cell, we must keep in mind that most of the electronic elements we have today are designed to help to humans but this does not mean that they have AI .

Having clear that AI is the intelligence demonstrated by the machines a question comes to mind, and is it. What is artificial intelligence used for? Nowadays we use AI to facilitate more and more the work of humanity, a clear and very common example is google maps, this helps us to optimize routes in order to avoid traffic and not waste time.

Is AI the Same as Machine Learning?

Not really. Although the two terms are often used interchangeably, they are not the same, Artificial intelligence is a broader concept, while machine learning is the most common application of AI.

So now, having clear our concepts the goal of machine learning generally is to understand the structure of data and fit that data into models that can be understood and utilized by people. It sounds Greek to me... but don't worry, things are simpler than they appear and the best way to explain it, is through everyday examples.

According to experience and the passing of the days we can predict when it will start raining, and this is simply for every time it rained, we realized that the sky was turning dark, the clouds looked great, even the wind was rising and it was cold . This can be considered Machine Learning because the data collection would be the experience of the previous rains, understanding the data would be the characteristics that are perceived from the sky before it rains and from this it creates a model that will be understood next time it's going to rain.

Yeah You rock! I know that now everything is clear to you, but...

There are two categories of Machine Learning problems:

Supervised learning and Unsupervised learning,.

Supervised learning is the most used between the two. It is called that because the form of presentation of the data serve as a guide to teach the algorithm about predictions that must be reached. that is, it generates models to predict a variable depending on the previous outputs of this variable.

If you wanted to predict the price of a beer and had an analysis of price data based on quality, supervised learning could be used to find a model to predict the price of a beer depending on its quality in the future .

And unsupervised learning uses information that is not classified, thus allowing the algorithm to act on that information without guidance.

if we take the example of beer again, if we do not have the data organized as supervised learning but we have a history of beers and quality and try to find a way to classify groups of beers. for this we can use unsupervised learning to group groups of beers based on quality and see if there are patterns for these results.

Neural Network

Is a graph with nodes. As the neurons in a brain:

Neural Networks have three layers: the input, the hidden layer (or layers) and the output, Neural Networks are a technique for supervised learning.