Content of Learning Activity

This course deals with advances in artificial intelligence through deep learning applied to the modeling of temporal sequences with long-term dependencies, and in particular to natural language processing:
- Contemporary AI using deep neural networks: DNN, CNN, RNN, LSTM, GRU, Attention, Transformers, GPT, generative models, GANs, auto-encoders, etc.
- Applications to natural language processing: natural language processing (NLP) and modeling, machine translation (neural machine translation), text classification and document information extraction, "chatbots" and answering questions, extraction and search of information in "big data" unstructured text / images, human-computer dialogue systems, situated interaction (language + vision) for example in games, text generation.
- Artificial intelligence models comprising billions of parameters and able to memorize and exploit the structure of language as well as knowledge and facts; importance of studying the equity and biases of AI in this context.
- You will also be offered articles for reading, in order to better understand the wide range of possible applications of these models: mining, infectiology, smart cities, traffic prediction, etc.

This course will include practicals to acquire the theory.
 

Required Learning Resources/Tools

All learning resources and tools required for this cours are available via Moodle, the online e-learning platform of UMONS.

Recommended Learning Resources/Tools

Additional recommended material is also accessible through Moodle, the online e-learning platform of UMONS.

Other Recommended Reading

Not applicable

Mode of delivery

• Face-to-face

Type of Teaching Activity/Activities

• Cours magistraux
• Travaux pratiques
• Travaux de laboratoire
• Projet sur ordinateur

Evaluations

The assessment methods of the Learning Activity (AA) are specified in the course description of the corresponding Educational Component (UE)