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.