This website uses cookies

The website of the Universitat Politècnica de Catalunya uses its own and third-party cookies to improve the browsing experience and for statistical purposes. For more information about cookies you can consult the cookie policy.

Accept only selected ones
Allow all cookies
Show details
ABOUT

Cookies are small text files that can be used by websites to make a user's experience more efficient.
The law states that we can store cookies on your device if they are strictly necessary for the operation of this site. For all other types of cookies we need your permission.
This site uses different types of cookies. Some cookies are placed by third party services that appear on our pages.
You can at any time change or withdraw your consent from the Cookie Declaration on our website.
Learn more about who we are, how you can contact us and how we process personal data in our privacy Policy.
When contacting us regarding your consent, please indicate your identification and the date of your consent.

COOKIE DECLARATION
Necessary :

Necessary cookies help make a website usable by enabling basic functions like page navigation and access to secure areas of the website. The website cannot function properly without these cookies.

Name Provider Purpose Expiry Type
lang www.fpc.upc.edu Save the web display language 2 years HTTP
politica_cookie www.fpc.upc.edu Save the general consent of cookies in the current domain. 1 year HTTP
cookie_estadistiques www.fpc.upc.edu Save the consent of statistical cookies in the current domain. 1 year HTTP
cookie_marketing www.fpc.upc.edu Save the consent of marketing cookies in the current domain. 1 year HTTP
PHPSESSID www.fpc.upc.edu Preserves user session state across page requests. Sessió HTTP
CONSENT [x3] Google Used to detect if the visitor has accepted the marketing and analytics category in the cookie banner. This cookie is necessary for GDPR-compliance of the website. 2 years HTTP
Statistics :

Statistic cookies help website owners to understand how visitors interact with websites by collecting and reporting information anonymously.

Name Provider Purpose Expiry Type
_ga Google Registers a unique ID that is used to generate statistical data on how the visitor uses the website. 2 years HTTP
_ga_# Google Used by Google Analytics to collect data on the number of times a user has visited the website as well as dates for the first and most recent visit. 2 years HTTP
_gat Google Used by Google Analytics to throttle request rate 1 day HTTP
_gid Google Registers a unique ID that is used to generate statistical data on how the visitor uses the website. 1 day HTTP
Marketing :

Marketing cookies are used to track visitors across websites. The intention is to display ads that are relevant and engaging for the individual user and thereby more valuable for publishers and third party advertisers.

Name Provider Purpose Expiry Type
last_campaign www.fpc.upc.edu Save the last campaign for which the user has reached the website. 6 months HTTP
campaign_XX www.fpc.upc.edu Save the last campaign for which the user has reached the website. 6 months HTTP
ads/ga-audiences Google Used by Google AdWords to re-engage visitors that are likely to convert to customers based on the visitor's online behaviour across websites. S Sessió Pixel
NID Google Registers a unique ID that identifies a returning user's device. The ID is used for targeted ads. 6 months HTTP
bcookie LinkedIn Used by the social networking service, LinkedIn, for tracking the use of embedded services. 2 years HTTP
bscookie LinkedIn Used by the social networking service, LinkedIn, for tracking the use of embedded services. 2 years HTTP
lidc Used by the social networking service, LinkedIn, for tracking the use of embedded services. 1 day HTTP
i/jot Twitter Inc. Sets a unique ID for the visitor, that allows third party advertisers to target the visitor with relevant advertisement. This pairing service is provided by third party advertisement hubs, which facilitates real-time bidding for advertisers. Session Pixel
_fbp [x2] Meta Platforms, Inc. Used by Facebook to deliver a series of advertisement products such as real time bidding from third party advertisers. 3 months HTTP
Campus
MY_TECH_SPACE

Go
Campus in maintenance
User and / or password incorrect
You have no active environment
Your access has been restricted. Consultation with the department of administration
Due to technical problems, the virtual campus is inaccessible. We are working to solve it. Sorry for the inconvenience.
Start   >  Events  >  Open Class "Deep Learning: The Transformer Revolution"
Date: 28-09-2022
Timetable: 8:00 pm to 9:30 pm
Location: Online
Contact: 937068035

An Open Class is to be held at 08:00 PM on wednesday 28-09-2022 on Postgraduate in Artificial Intelligence with Deep Learning (Face-to-face) and Postgraduate in Artificial Intelligence with Deep Learning (Online).

Deep learning has achieved remarkable results in fields including computer vision, speech recognition and natural language processing. Some of the most important breakthroughs in recent years have taken place thanks to the Transformer, a type of neural network based on the attention mechanism. This architecture, which initially brought about a significant improvement in machine translation, has revolutionised a wide range of research fields, and even impact beyond natural language processing.

In this talk, Gerard I. Gállego will provide an introduction to the Transformer and discuss its most important applications. The session will begin with an introduction to the attention mechanism, which is the main component of the Transformer. He will then define the modules that are part of its basic architecture. Afterwards, he will describe the best-known variants of Transformer, such as BERT and GPT-3, and their most important characteristics. Finally, he will present some applications of the Transformer that have transcended fields beyond written language processing from a more general point of view.

This openclass will take place in English.

The speaker

Gerard I. Gállego holds a degree in Telecommunication Technologies and Services Engineering from the Universitat Politècnica de Catalunya (UPC) and a master's degree in Advanced Telecommunication Technologies, specializing in Deep Learning for Multimedia Processing. He is PhD student in Machine Translation at the Department of Signal Theory and Communications at the UPC, and the co-director of the master's degree in Artificial Intelligence with Deep Learning at the UPC School.

The session will take place on-line using Google Meet.

As well, you can follow the Open Class using your mobile device by downloading the corresponding Google Meet application for your Android or iOS.

This event is open and free. To attend, please confirm using the "I Will attend". Limited places.

I will attend

Registration received!
After we have registered your request, you will receive confirmation of your place by email.

Thank you for your interest.
Error
Due to an error in the connection to the database, your submission has not been processed. Please try again later, phone us on (34) 93 112 08 08, or send us an email at: webmaster.fpc@fpc.upc.edu



If, in addition to enrolling in the Open Class, you are interested in the training program, select this option:

  date protection policy

* Mandatory fields

Información básica o primera capa sobre protección de datos

Responsable

Fundació Politècnica de Catalunya (en adelante, FPC). + INFORMACIÓN

Finalidad

Contestar a las solicitudes de información del interesado sobre actividades de formación gestionadas o realizadas por la FPC. + INFORMACIÓN

Establecimiento o mantenimiento de relación académica con el interesado. + INFORMACIÓN

Legitimación

Consentimiento del interesado. + INFORMACIÓN

Interés legítimo en el desarrollo de la relación académica. + INFORMACIÓN

Destinatarios

No existen cesiones o comunicaciones.

Derechos

Acceso, rectificación, supresión, limitación, oposición y portabilidad. + INFORMACIÓN

Datos de contacto del delegado de protección de datos

info.dpo@fpc.upc.edu

Información adicional

Política de Privacidad de nuestra página Web. + INFORMACIÓN

Plazo de conservación

Política de Privacidad de nuestra página Web. + INFORMACIÓN

Cesión de imagen

Aceptación a la cesión, por un periodo de 10 años, las imágenes que la FPC pueda captar en las instalaciones donde se desarrolle su actividad, a fin de difundir y promocionar las actividades de la FPC y por el medio que esta tenga por conveniente.

Servicios de pago

En caso que el interesado formalice la relación con la FPC, el ordenante (interesado) autoriza y da su consentimiento al cargo, por tanto, con renuncia expresa al derecho de devolución sobre el cargo.


Send