Les commentaires sont clos.

postdoc positions in neuromorphic engineering

23 Septembre 2020

Catégorie : Post-doctorant

Two postdoc positions are available at the Loria laboratory, University of Lorraine, in Nancy, France.

Supervision: Bernard Girau

Duration: 12 months

Contact: Bernard.Girau at

The positions are expected to be available starting October 2020. Applications will be continuously received until the positions are filled.

Postdoc 1:

Neuromorphic architectures: spiking neural fields on digital neuromorphic chips.

Postdoc 2:

Self-organizing hardware architectures: self-organizing maps on a reconfigurable multicore architecture.


Postdoc 1 summary
This postdoc proposal first aims to study how spiking versions of dynamic neural fields can be implemented on neuromorphic circuits that have emerged recently, such as the Intel Loihi architecture, in terms of computation and communication. The main illustrative application will be to track targets in a visual scene captured by a DVS spiking camera. The question of the implementation of neural architectures with several neural fields connected to each other will also be addressed, with applications to visual attention and visual memory. Finally, on the basis of a spiking version of self-organizing maps (SOM) that uses local STDP learning rules, an additional objective will be the evaluation of the capacity of this model to be mapped onto the Loihi chip.
Postdoc 2 summary
We are interested in the design of adaptive and dynamic computing architectures, taking advantage of brain-inspired principles of structural plasticity. The objective of the work proposed here is to make the link between a reconfigurable multi-core architecture capable of exploiting the principles of hardware self-organization on one hand, and different models of self-organizing maps that integrate mechanisms of structural plasticity on the other hand. The two main tasks are:
- to study the implementation of self-organizing map models featuring structural plasticity on the multi-core reconfigurable board, by analyzing their behavior when dealing with real-world data and their properties with respect to the board's communication constraints
- to interpret the vector quantization learned by the self-organizing maps in terms of communication needs among the computing units of the self-organizing architecture and in terms of dynamic allocation of computing resources within the board