Spiking Neural Network Based on Cusp Catastrophe Theory
[ 1 ] Instytut Informatyki, Wydział Informatyki, Politechnika Poznańska | [ P ] employee
2019
scientific article
english
- spiking neuron
- cusp catastrophe
- decision support system
- XOR problem
EN This paper addresses the problem of effective processing using thirdgeneration neural networks. The article features two new models of spiking neuronsbased on the cusp catastrophe theory. The effectiveness of the models is demonstratedwith an example of a network composed of three neurons solving the problem of linearinseparability of the XOR function. The proposed solutions are dedicated to hardwareimplementation using the Edge computing strategy. The paper presents simulationresults and outlines further research direction in the field of practical applicationsand implementations using nanometer CMOS technologies and the current processingmode.
28.08.2019
273 - 284
CC BY-NC-ND (attribution - noncommercial - no derivatives)
open journal
final published version
in press
public
20
40