UMR CNRS 7253

Site Tools


en:projects

European Projects

MASH

The MASH project investigates the design of complex learning systems to increase the performance of artificial intelligence. To create such systems, we want to involve large groups of contributors from as many fields and backgrounds as possible, to program large and heterogeneous families of feature extraction modules.

This project is funded by the Information and Communication Technologies division of the European Commission, Cognitive Systems and Robotics unit, under the 7th Research Framework Program.

PASCAL II

The PASCAL Network of Excellence has created a distributed institute pioneering principled methods of pattern analysis, statistical modeling, and computational learning.PASCAL2 refocuses the Institute towards the emerging challenges created by the ever expanding applications of adaptive systems technology and their central role in the development of large scale cognitive systems.

This project is funded by the Information and Communication Technologies division of the European Commission, Cognitive Systems and Robotics unit, under the 7th Research Framework Program.

National Projects

DESSTOPT

DESSTOPT (Deep Semi-Supervised and Transfer Learning with Optimal Transport) is a CNRS PEPS IA3 academic research project (from the math and computer science instutes, INSMI and INS2I, in collaboration with AMIES) aiming at using techniques based on optimal transport for semi-supervised and transfer learning.

Everest

Everest is an ANR academic research project aiming at learning high-level representations of sparse tensors.

ClasSel

ClasSel ended in 2012. It was an ANR academic research project aiming at devising methods producing knowledge from data, by producing data summaries in a form readily amenable to interpretation. Data arrays are abstracted through the inference of homogeneous block-clusters, grouping jointly examples and variables. The project focuses on the fundamental problem of model selection in this type of models.


User Tools