Image recognition with LearningML | Mediateca de EducaMadrid

Welcome everybody to the tutorial Image Recognition with LearningML. 00:00:00

LearningML is a web platform for teaching and learning about machine learning 00:00:04

and is designed in the context of the Erasmus Plus project FIAS, 00:00:08

Fostering Artificial Intelligence at Schools. In this tutorial we will use the LearningML 00:00:12

application to build an AI model to classify images. A model is basically a mapping between 00:00:18

an input and an output . What we will do today is build a model 00:00:24

that classifies images of animals into four classes, crabs, butterflies, crocodiles and 00:00:29

kangaroos. Let's start and go to the web application. A link can also be found in the 00:00:35

description of this video. So we can choose between two versions, a stable and a beta version. 00:00:41

The beta version has more functionality, but it is still being tested. This means there still 00:00:48

might be errors or things not working exactly like they should. So for now, let's use the 00:00:53

stable version. We are interested in images, so we click on recognize images. 00:00:58

Here we see the three steps we will need to build our model. Train, learn and try. 00:01:04

These correspond to the different steps in machine learning, the AI technique we 00:01:11

will use to build our model. In machine learning models are trained and they 00:01:15

will learn how to classify images by looking at examples, called the training 00:01:20

examples. How many examples are needed depends on many factors. Using LearningML 00:01:24

for simple examples like ours, 10 examples per class would be the bare 00:01:30

minimum. So then, as a second step, these examples will be used to create the 00:01:34

model. More precisely, the algorithm behind this will learn a mapping from 00:01:40

images to the classes. And finally, we can test our model. Let's start with the 00:01:45

first step, adding our training examples, the data that will be used to train the 00:01:51

model. We have four classes, we have to add them one by one. So the first one is 00:01:56

butterfly, okay, the second one crab, okay, the third one crocodile, oops, and the 00:02:05

last one is kangaroo. Now we add images to each of these classes. You can add 00:02:23

images saved on your computer and you can also use a webcam. So I don't have a 00:02:33

crocodile sitting around at home so I will upload images from my computer. So I 00:02:39

have already prepared the images. I have examples of all four classes and I also 00:02:48

have some test examples. The latter are images that are not present in the 00:02:52

training example. So I can test how well the model performs on images it has 00:02:57

never seen before. So let's add the images. So first we start with the 00:03:01

kangaroos. So let's add all of them at once. Then let's go to the crocodiles. So 00:03:06

again, upload them all at once. And then the crabs. And finally the butterflies. 00:03:16

So, and then the second step is learning how to recognize the images. 00:03:39

So this step could take a while since it is computationally hard. 00:03:47

So let's wait a bit for that. 00:03:52

Okay, so now we can verify how accurate our model is. 00:04:07

So we'll test the model on an image it has not seen before. 00:04:12

So an image not included in the training examples. 00:04:16

so let's go to the test folder and let's pick this one okay so it's pretty sure that it belongs 00:04:18

to the class crap so what basically happens is that for each class it gives a probability 00:04:28

kind of confidence that the image belongs to that class so this example is classified as a crap 00:04:33

because there is an over 95 percent of confidence that it belongs to that class 00:04:40

So let's try something else. Let's try another one of our test examples. So this one, 00:04:46

this should be a butterfly. And yes, it is. 88% probability. 00:04:52

Now let's try something completely different. What would happen if I upload the image of this 00:04:59

animal? Well, it is a butterfly. So this seems to make no sense, but it actually does. The 00:05:08

model has only learned how to map an image to one of the four classes it does not know anything 00:05:15

besides those four classes so according to the training data this cat resembles a butterfly 00:05:21

so now you can save your project you can either download the copy to your computer or save it 00:05:30

in the cloud if you have a learning ml account so next time you can open the project either by 00:05:36

uploading it for your computer or from your account and it will contain all the classes 00:05:44

and the training examples already loaded. This means you can also open projects created by 00:05:49

someone else. Several examples can be found on the LearningML website and also on our FIAS project 00:05:54

page. The images used for the animal classifier we created today can be found on the LearningML 00:06:00

website. You can find the link in the description of this video. In the next video we will see how 00:06:06

we can use the model in our programming platform. See you then! 00:06:12

Image recognition with LearningML - Contenido educativo

Del mismo autor…

FESTIVAL DE NAVIDAD 2025

DESCUBRIMOS LA PREHISTORIA. ASHLEY

DESCUBRIMOS LA PREHISTORIA. INAYA

DESCUBRIMOS LA PREHISTORIA. AMIN

DESCUBRIMOS LA PREHISTORIA. LEAH

DESCUBRIMOS LA PREHISTORIA. FATIMA

DESCUBRIMOS LA PREHISTORIA. GINEVRA