Neural Networks: Birth, Death and Resurrection

Patrick Gallinari is professor in Computer Science at Université Sorbonne in Paris. His research focuses on statistical learning with applications in fields such as semantic data analysis and complex data modeling. His recent work deals with the modeling of structured data. He leads a team whose main theme is Learning Representations and Deep Learning (https://mlia.lip6.fr/). In the old days, he has been one of the pioneers in the development of neural networks in France. He was also director of the computer lab. of Paris 6 (Jussieu) from 2005 to 2013.

The recent rise of modern Artificial Intelligence has been supported by large scale operational deployments of machine learning algorithms. The dominant technology today in this field is Deep Learning, the modern name of an older technology – Artificial Neural Networks. Is there something special about these methods that make them different from alternative machine learning or statistical techniques? What are the future evolutions of this domain? Is it only a new episode of the Neural Network saga or is it the sign of a deeper and definitive evolution of AI? I will draw an historical perspective on the domain, introducing the main challenges, concepts and evolutions of the field. I will describe some of the recent advances and try to put in evidence some future challenges. This will be illustrated via several application domains in the field of semantic data analysis.