¿Cuáles son los objetivos de Aepia?

Aepia es una asociación formada por docentes, investigadores y profesionales que comparten intereses en temas relacionados con la Inteligencia Artificial.

Ver más información...

La Conferencia de la Asociación Española para la Inteligencia Artificial (CAEPIA) es un foro bienal abierto a investigadores de todo el mundo para presentar y discutir los últimos avances científicos y tecnológicos en Inteligencia Artificial. Como en las anteriores ediciones, los objetivos son: facilitar la diseminación de nuevas ideas y experiencias, fortalecer los lazos entre los distintos grupos de investigación implicados, promover el trasvase de conocimiento entre nuevos investigadores y grupos consolidados, y ayudar a difundir los nuevos desarrollos hacia la sociedad. En esta ocasión, se celebra en el contexto del VI Congreso Español de Informática (CEDI 2020). Nueva fecha para enviar artículos LNAI: 19 abril 2020

Visitar la web de la conferencia...

DEEP LEARNING FOR NATURAL LANGUAGE PROCESSING (6th edition)

San Sebastian, Spain, 1-3 July, 2020 

20 hour, 3 day crash summer course

http://ixa2.si.ehu.es/deep_learning_seminar/ 

============================================================================ 

COVID update: Instead of physical attendance, the classes will be broadcasted live online. The practical labs will be also held online, in two split groups with one lecturer in each. Given our online teaching experience these last weeks, we are confident that we will be able to offer a high-quality and engaging course, both at the theoretical and hands-on practical sessions. 

Deep Learning neural network models have been successfully applied to natural language processing, and are now changing radically how we interact with machines (Siri, Amazon Alexa, Google Home, Skype translator, Google Translate, or the Google search engine). These models are able to infer a continuous representation for words and sentences, instead of using hand-engineered features as in other machine learning approaches. The seminar will introduce the main deep learning models used in natural language processing, allowing the attendees to gain hands-on understanding and implementation of them in Keras. 

This course is a 20 hour introduction to the main deep learning models used in text processing, covering the latest developments, including Transformers and pre-trained (multilingual) language models like GPT, BERT and XLM. It combines theoretical and practical hands-on classes. Attendants will be able to understand and implement the models in Keras. 

----------------STUDENT PROFILE---------------- 

Addressed to professionals, researchers and students who want to understand and apply deep learning techniques to text. The practical part requires basic programming experience, a university-level course in computer science and experience in Python. Basic math skills (algebra or pre-calculus) are also needed. 

----------------CONTENTS---------------- 

- Introduction to machine learning and NLP with Keras 

- Multilayer Perceptron and Word Embeddings 

- Recurrent Neural Networks, Seq2seq, Neural Machine Translation 

- Attention, Better Machine Translation and Natural Language Inference 

- Convolutional neural networks. Pre-trained Language Models 

----------------INSTRUCTORS---------------- 

- Eneko Agirre, Full professor, member of IXA 

- Oier Lopez de la Calle, Postdoc researcher at IXA 

- Ander Barrena, Postdoc researcher at IXA 

----------------PRACTICAL DETAILS----------------

Part of the Language Analysis and Processing master program (http://ixa.eus/master) 

5 theoretical sessions with interleaved labs, 20 hours 

Scheduled July 1st to 3rd 2020, 9:00-13:00 14:30-18:30 (Friday ends 16:00). 

 

Teaching language: English 

Capacity: 60 attendants (First-come first-served). 

Cost: 274 euros (270 for UPV/EHU members). 

----------------REGISTRATION---------------- 

Registration open: now to the 20th of June 2020 (or until room is full). 

Please register by email to Esta dirección de correo electrónico está siendo protegida contra los robots de spam. Necesita tener JavaScript habilitado para poder verlo. (subject "Registration to DL4NLP" and CC Esta dirección de correo electrónico está siendo protegida contra los robots de spam. Necesita tener JavaScript habilitado para poder verlo.). 

Same for any enquiry you might have. 

 

----------------PREREQUISITE---------------- 

Basic programming experience, a university-level course in computer science and experience in Python. Basic math skills (algebra or pre-calculus) are also needed. 

Computer with Internet needed (no need to install anything).

Inscríbete en Aepia

Easy to startDisfruta de las ventajas de ser socio de AEPIA.

Leer más...

Socios institucionales

Native RTL SupportConoce los socios institucionales de AEPIA.

Leer más...

Grupos de I+D en IA

Native RTL SupportConoce los grupos de investigación que desarrollan su labor en alguna de las áreas de la Inteligencia Artificial.

Leer más...

Joomla templates by Joomlashine