Title :
Effect of synaptic weight assignment on spiking neuron response
Author :
Fujii, Robert H. ; Ichishita, Taiki
Author_Institution :
Univ. of Aizu, Aizu-Wakamatsu
Abstract :
Three synaptic weight assignment schemes were proposed and their effect on the behavior of a spiking neuron was analyzed. To evaluate the proposed synaptic assignment schemes, a feed-forward Spiking Neural Network that can learn to recognize temporal sequences was proposed. This spiking neural network uses two of the proposed synaptic weight assignment schemes in conjunction with a spiking neuron model that uses a simplified linear soma potential function. The robustness and reliability of the proposed spiking neural network system were shown by the high (approximately 99%) temporal sequence recognition rate achieved during testing. Practical hardware implementation issues were also discussed.
Keywords :
feedforward neural nets; feedforward spiking neural network; linear soma potential function; spiking neuron response; synaptic weight assignment; Artificial neural networks; Biological information theory; Biological neural networks; Biological system modeling; Intersymbol interference; Nerve fibers; Neural networks; Neurofeedback; Neurons; Recurrent neural networks;
Conference_Titel :
Machine Learning and Applications, 2007. ICMLA 2007. Sixth International Conference on
Conference_Location :
Cincinnati, OH
Print_ISBN :
978-0-7695-3069-7
DOI :
10.1109/ICMLA.2007.16