Section: New Results

Embodied and embedded systems

Participants : Yann Boniface, Hervé Frezza-Buet, Bernard Girau, Mathieu Lefort.

InterCell

Our research in the field of dedicated architectures and connectionist parallelism mostly focuses on embedded systems (cf. § 3.5 ). Nevertheless we are also involved in a project that considers coarse-grain parallel machines as implementation devices. The core idea of this InterCell project (cf. http://intercell.metz.supelec.fr ) is to map fine grain computation (cells) to the actual structure of PC clusters. The latter rather fit coarse grain processing, using relatively few packed communication, which a priori contradicts neural computing. Another fundamental feature of the InterCell project is to promote interaction between the parallel process and the external world. Both features, cellular computing and interaction, allow to consider the use of neural architectures on the cluster on-line, for the control of situated systems, as robots.

Hardware implementations of neural models

In the field of dedicated embeddable neural implementations, we use our expertise in both neural networks and FPGAs so as to propose efficient implementations of applied neural networks on FPGAs, as well as to define hardware-friendly neural models.

• We currently intend to minimize the topological constraints of FPGA-embedded spiking neural fields using reduced neighborhoods but randomly propagating spikes. A preliminary result has been obtained so as to implement massively distributed pseudo-random number generators based on cellular automata that use minimal areas though they produce random streams that pass most randomness tests [19] . These results have also been applied to cellular aurtomata using randomnes in their transition rules [13] .

• Researchers have proposed the concept of Central Pattern Generators (CPGs) as a neural mechanism for generating an efficient control strategy for legged robots based on biological locomotion principles. We have developed a reconfigurable hardware implementation of a CPG‐based controller which is able to generate several gaits for quadruped and hexapod robots [3] .

Towards brain-inspired hardware

Our activities on dedicated architectures have strongly evolved in the last years. We now focus on the definition of brain-inspired hardware-adapted frameworks of neural computation. Our current works aim at defining hardware-compatible protocols to assemble various perception-action modalities that are implemented and associated by different bio-inspired neural maps.

Multimodal learning through joint dynamic neural fields

This work relates to the development of a coherent multimodal learning for a system with multiple sensory inputs. We have modified the BCM synaptic rule, a local learning rule, to obtain the self organization of our neuronal inputs maps and we use a CNFT based competition to drive the BCM rule. In practice, we introduce a feedback modulation of the learning rule, representing multimodal constraints of the environment, and we introduce an unler-arning term in the BCM equation to solve the problem of the different temporalities between the raise of the activity within modal maps and the multimodal learning of the organization of the maps [1] , [26] .

Randomly spiking dynamic neural fields

We have defined a new kind of spiking neural field that is able to use only local links while transmitting spikes through the map by succesive random propagations. Such a model is able to be mapped onto FPGAs, while maintaining most properties of neural fields. Early results will be soon published.