nireEHU 
Subject
Deep Learning
General details of the subject
- Mode
- Face-to-face degree course
- Language
- English
Description and contextualization of the subject
Los modelos de redes neuronales de Aprendizaje Profundo (Deep Learning) se han aplicado con éxito al procesamiento del lenguaje natural, y están cambiando radicalmente la forma en que interactuamos con las máquinas (Siri, Amazon Alexa, Google Home, el traductor de Skype, Google Translate o el motor de búsqueda de Google). Estos modelos infieran una representación continua tanto para palabras como para oraciones, en lugar de utilizar los rasgos diseñadas a mano de otros enfoques de aprendizaje automático. El curso presentará los principales modelos de aprendizaje profundo utilizados en el procesamiento del lenguaje natural, lo que permitirá a los asistentes comprender e implementar estos modelos en Tensorflow.Teaching staff
| Name | Institution | Category | Doctor | Teaching profile | Area | |
|---|---|---|---|---|---|---|
| AGIRRE BENGOA, ENEKO | University of the Basque Country | Profesorado Pleno | Doctor | Bilingual | Computer Languages and Systems | e.agirre@ehu.eus |
| AZCUNE GALPARSORO, GORKA | University of the Basque Country | Profesorado Agregado | Doctor | Bilingual | Science of Computation and Artificial Intelligence | gorka.azcune@ehu.eus |
| BARRENA MADINABEITIA, ANDER | University of the Basque Country | Profesorado Adjunto (Ayudante Doctor/A) | Doctor | Bilingual | Computer Languages and Systems | ander.barrena@ehu.eus |
| LOPEZ DE LACALLE LECUONA, OIER | University of the Basque Country | Profesorado Adjunto (Ayudante Doctor/A) | Doctor | Bilingual | Computer Languages and Systems | oier.lopezdelacalle@ehu.eus |
Competencies
| Name | Weight |
|---|---|
| Learn skills to deal with strategies and tools for natural language processing. | 20.0 % |
| Learn skills to deal with machine learning methods for natural language processing. | 20.0 % |
| Ability to manage, adapt and improve the most relevant empirical methods for research in language technologies. | 20.0 % |
| Ability to handle multimodal representations. | 20.0 % |
| Ability to improve language understanding with visual information. | 20.0 % |
Study types
| Type | Face-to-face hours | Non face-to-face hours | Total hours |
|---|---|---|---|
| Lecture-based | 20 | 30 | 50 |
| Applied laboratory-based groups | 40 | 60 | 100 |
Training activities
| Name | Hours | Percentage of classroom teaching |
|---|---|---|
| Computer work practice, laboratory, site visits, field trips, external visits | 100.0 | 40 % |
| Lectures | 50.0 | 40 % |
Assessment systems
| Name | Minimum weighting | Maximum weighting |
|---|---|---|
| Works and projects | 0.0 % | 100.0 % |
Learning outcomes of the subject
Show understanding of deep learning systems, as well as the main architectures used in NLPDevelopment of basic deep learning systems applied to NLP problems.
Show knowledge about the latest advances in deep learning for NLP
Temary
1. Introduction to machine learning and NLP with Tensorflow2. Multilayer Perceptron
3. Word embeddings and recurrent neural networks
4. Seq2seq, neural machine translation and better RNNs
5. Attention, Neural machine Translation and Natural Language Inference
6. Transfer learning
7. Bridging the gap between natural languages and the visual world
8. Convolutional neural networks for text
Bibliography
Basic bibliography
Yoav Goldberg's Primer. http://u.cs.biu.ac.il/~yogo/nnlp.pdfKyunghyun Cho¿'s course notes. http://arxiv.org/pdf/1511.07916.pdf
The online version of the Goodfellow, Bengio, and Courville Deep Learning textbook. http://www.deeplearningbook.org/