AUTHOR=Heidarpur Moslem , Ahmadi Arash , Ahmadi Majid 

TITLE=The silence of the neurons: an application to enhance performance and energy efficiency

JOURNAL=Frontiers in Neuroscience

VOLUME=Volume 17 - 2023

YEAR=2024

URL=https://www.frontiersin.org/journals/neuroscience/articles/10.3389/fnins.2023.1333238

DOI=10.3389/fnins.2023.1333238

ISSN=1662-453X

ABSTRACT=Simulation of biological neural networks is a computationally intensive task due to number of neurons, various communication pathways and nonlinear terms in neuron's differential equations. This work proposes an original modification to optimize performance and power consumption in systems simulating or implementing spiking neural networks. First, proposed modified models were simulated for validations. Further, a digital hardware were designed and both original and proposed models were implemented on Field Programmable Gate Array (FPGA). Moreover, impact of the proposed modification on performance metrics were studied. Implementation result confirmed that proposed models are considerably faster and require less energy to generate a spike comparing with unmodified neuron.