Saltar navegación

Activa JavaScript para disfrutar de los vídeos de la Mediateca.

Curso IA programamos.es -- cómo entienden el mundo los orden (eng) - Contenido educativo

Ajuste de pantalla

El ajuste de pantalla se aprecia al ver el vídeo en pantalla completa. Elige la presentación que más te guste:

Subido el 29 de marzo de 2024 por David G.

12 visualizaciones

Más información Transcripción

Descargar la transcripción

People perceive the world through our senses, but how do machines perceive 00:00:01
the world? Computers use different types of sensors, like microphones, 00:00:05
cameras, radars, or GPS receivers, among others, to receive information from the environment 00:00:11
that surrounds them and build a representation of their surroundings. But computers only understand 00:00:17
working with numbers, so all the information they receive from their sensors has to be 00:00:22
stored as a set of numbers. For example, a black and white image is encoded 00:00:27
as a matrix of numbers, where each value indicates the brightness of each pixel. 00:00:31
If the image is in color, three numbers are stored for each pixel, representing the 00:00:36
brightness of the red, green, and blue components. Sounds are also encoded as a 00:00:41
series of numbers, indicating the waveform values at different moments, 00:00:46
taking hundreds or thousands of samples per second. 00:00:51
And the fact that a machine can receive information from the world already makes it an artificial intelligence system? 00:00:54
Well, no, for us to consider it as such, it needs to be able to extract meaning from that information. 00:01:01
Let's think about a supermarket door that opens when a sensor detects movement. 00:01:07
The system is too simple to be able to perceive who or what is entering 00:01:12
and make decisions based on this meaning. 00:01:17
And thanks to this limitation, we can enjoy wonderful videos of wild animals strolling through supermarket aisles, as Turesky and Garner joke in their chapter on AI literacy in this magnificent work. 00:01:20
But how do computers extract meaning from a set of numbers that represents 00:01:35
an image, for example? 00:01:42
This signal to meaning transformation occurs in progressive stages through 00:01:44
a process called feature extraction. 00:01:50
On the screen, we have an image of a number 4 written by a person that the computer 00:01:55
has already encoded into a matrix of numbers from the information of its camera. 00:01:59
But how could it know that it is a 4 and not a 1 or a 7? 00:02:04
By looking for specific combinations of values representing light and dark pixels 00:02:09
in small areas of the image, in this case 3x3 pixels, the location can be detected 00:02:13
and the orientation of different edges in the image. 00:02:20
Thus, the result of applying a filter to detect left edges is shown in the 00:02:24
image on the right, where areas detected as left edges appear 00:02:30
marked in red. Opposite areas are shown in blue, meaning in this case the right edges. 00:02:34
Now let's apply a filter to detect upper edges. See? So, through this 00:02:40
progressive stage process of feature extraction, where different 00:02:49
types of filters are used and combined, a signal is transformed into meaning. With sounds, it's done 00:02:54
something very similar, for example for speech recognition, since each vowel and each 00:03:02
consonant can be associated with different patterns of a spectrogram, which is a representation 00:03:07
visual that allows identifying the different variations of frequency and intensity of the 00:03:13
sound. But there are AI systems that not only can translate 00:03:17
an audio into text, but also seem to understand these texts. But how can this be? 00:03:22
How is this possible? Well, that's precisely what we'll see in the next video. 00:03:28
Idioma/s:
es
Idioma/s subtítulos:
en
Autor/es:
Programamos.es
Subido por:
David G.
Licencia:
Reconocimiento
Visualizaciones:
12
Fecha:
29 de marzo de 2024 - 17:53
Visibilidad:
Público
Centro:
IES MARIE CURIE Loeches
Duración:
03′ 33″
Relación de aspecto:
1.78:1
Resolución:
854x480 píxeles
Tamaño:
20.11 MBytes

Del mismo autor…

Ver más del mismo autor

EducaMadrid, Plataforma Educativa de la Comunidad de Madrid

Plataforma Educativa EducaMadrid