Section: New Results
Large and Deep Networks
Participants : Ludovic Arnold, Sylvain Chevallier, Anthony Mouraud, Hélène Paugam-Moisy, Sébastien Rebecchi, Michèle Sebag.
- Deep networks: RBM or AA
The two main families of deep networks are implemented and studied by TAO: stacked RBM (Restricted Boltzmann Machines) and stacked AA (Auto-Associators).
- Learning sparse features for deep networks
Inspired by the theory of compressed sensing and beyond the common methods based on dictionary learning, we have proposed to learn sparsity and accuracy simultaneously by alternating two constraints on the weights of an Auto-Associator  .
- Spiking neuron networks for swarm robotics
The model "SpikeAnts"  has been applied to a spatial robotic environment  , in collaboration with Nicolas Bredeche (see Section 6.2 , and has demonstrated even more its interest in the context of swarm robotics.