A class of fully asynchronous Spiking Neural Networks is proposed, in which the latency time is the basic effect for the spike generation. On the basis of the classical neuron theory, all the parameters of the systems are defined and a very simple and effective analog simulator is developed. The proposed simulator is then applied to elementary examples in which some properties and interesting applications are discussed.
Salerno, M., Susi, G., D’Annessa, A., Cristini, A., Sanfelice, Y. (2012). Spiking neural networks as analog dynamical systems: basic paradigm and simple applications. In Computer Science and Communication Devices - EDC 2012, CSA 2012, SPC 2012, ACE 2012 (pp.17-23). Amsterdam -- NLD : IDES-CPS.
Spiking neural networks as analog dynamical systems: basic paradigm and simple applications
SALERNO, MARIO;SUSI, GIANLUCA;
2012-01-01
Abstract
A class of fully asynchronous Spiking Neural Networks is proposed, in which the latency time is the basic effect for the spike generation. On the basis of the classical neuron theory, all the parameters of the systems are defined and a very simple and effective analog simulator is developed. The proposed simulator is then applied to elementary examples in which some properties and interesting applications are discussed.| File | Dimensione | Formato | |
|---|---|---|---|
|
10(11).pdf
accesso aperto
Dimensione
197.18 kB
Formato
Adobe PDF
|
197.18 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
