Fraunhofer-Gesellschaft

Publica

Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

Biologically-inspired artificial neurons. Modeling and applications

 
: Scholles, M.; Hosticka, B.J.; Richert, P.; Schwarz, M.

:

Institute of Electrical and Electronics Engineers -IEEE-:
IJCNN '93. International Joint Conference on Neural Networks. Proceedings
Piscataway/N.J., 1993
ISBN: 0-7803-1421-2
pp.2300-2303
International Joint Conference on Neural Networks <1993, Nagoya>
English
Conference Paper
Fraunhofer IMS ()
adaption; adaptive system; Biokybernetik; biological cybernetics; Impulsfolge; learning; Lernen; mathematisches Modell; neural network; neuronales Netzwerk; pulse train; range; Schallortung; signal delay; Signalverzögerung; sonar; sound location; sound navigation

Abstract
Currently used neural networks employ mostly simple neuron models that greatly differ from the "real" biological neurons. To ensure progress in biology-based neural processing, more advanced neuron models must be developed that better reflect the biological functionality. In this communication, we investigate a neuron model which satisfies such requirements to a much higher degree. We also examine some of its learning properties and look at its applications.

: http://publica.fraunhofer.de/documents/PX-6718.html