Embedded neural controllers based on spiking neuron models

Bakó, László and Brassai, Sándor (2009) Embedded neural controllers based on spiking neuron models. Pollack Periodica, 4 (3). pp. 143-154. ISSN 1788-1994

Text pollack.4.2009.3.13.pdf Restricted to Repository staff only until 31 December 2029. Download (466kB)

Abstract

This paper demonstrates, that input patterns can be encoded in the synaptic weights by local Hebbian delay-learning of spiking neurons (SN), where, after learning, the firing time of an output neuron reflects the distance of the evaluated pattern to its learned input pattern thus realizing a kind of RBF behavior. Furthermore, the paper shows, that temporal spike-time coding and Hebbian learning is a viable means for unsupervised computation in a network of SNs, as the network is capable of clustering realistic data. Then, two versions — with and without embedded micro-controllers — of a SNN are implemented for the aforementioned task.

Actions (login required)

Edit Item