This paper proposes the use of approximate multipliers in the hardware implementation of Izhikevich spiking neuron model. The accuracy of the model is investigated by calculating various types of errors on a single neuron and this analysis shows that the proposed model follows the original model. It shows that the proposed model reproduces the same firing patterns as the original one. The network behavior is also studied and proved that the model has the same activity patterns of the original one. Moreover, the proposed neuron exhibits better accuracy than the piecewise linear approximation of the Izhikevich model.
|Original language||English (US)|
|Title of host publication||2018 IEEE 61st International Midwest Symposium on Circuits and Systems (MWSCAS)|
|Publisher||Institute of Electrical and Electronics Engineers (IEEE)|
|Number of pages||4|
|State||Published - Feb 26 2019|
Bibliographical noteKAUST Repository Item: Exported on 2020-10-01
Acknowledgements: This research was partially funded by ONE Lab at Cairo University, Zewail City of Science and Technology, and KAUST.