ok
Neural sytems
14/12/2012 09:00 | Durée 01:46:09

Intervenants : Alain Cappy , Directeur de Institut de Recherche en Composants logiciels et matériels pour l’Information et la Communication Avancée (IRCICA) ; Professeur d’électronique et physique des dispositifs à semi-conducteurs, Université de Lille – sciences et technologies ; De 2002 à 2009, directeur de l’Institut d’Électronique de Microélectronique et de Nanotechnologie (IEMN), Université Lille 1 .   Steve Furber , ICL Professor of Computer Engineering, the University of Manchester, UK .   Simon Thorpe , CerCo (Brain and Cognition Research Center) & SpikeNet Technology SARL, Toulouse, France .  

Spike-based Learning in Biological and Artificial Neural Networks Simon Thorpe (CerCo (Brain and Cognition Research Center) & SpikeNet Technology SARL, Toulouse, France) Abstract: I will argue that Spike-Time Dependent Plascity mechanisms (STDP) could provide a key to understanding how biological neural systems are able to learn to recognize complex repeating patterns. A combination of experimental and simulation studies have demonstrated that, thanks to STDP, neurons can become selective to a given stimulus after a few tens of presentations. Since STDP like learning can potentially be implemented in a range of different hardware systems, this opens the possiblity of developing memristor based artificial systems that could reproduce some of the most interesting features of biological neural systems. SpiNNaker: a spiking neural network architecture Steve Furber (ICL Professor of Computer Engineering, the University of Manchester, UK) Abstract: The SpiNNaker project is developing a massively-parallel computer, ultimately to incorporate over a million ARM processor cores, optimized for modeling large-scale systems of spiking neurons in biological real time. At present we have prototype systems with just under a thousand processors and a software suite that allows automated mapping of networks from a high-level description in a language such as PyNN or NENGO onto SpiNNaker, and various vision and robotics demonstrations on the system’s capabilities.