Abstract
This work presents a supervised training strategy applied to a biorealistic Spiking Neural Network (SNN) with feedforward 2-2-1 architecture. This network uses Izhikevich neurons with regular-spiking behavior. The input layer, which has 2 nodes, generates temporal pulse trains that pass through synaptic conductances. These conductances transform voltages into currents. The receiving currents by 2 hidden-neurons also generate voltage pulses into synaptic conductances towards the output neuron. Each synaptic conductance has 2-parallel Alpha functions, whose weighting factors are found by the Efficient Artificial Bee Colony Algorithm (EABC Algorithm). This is a variant of the Artificial Bee Colony Algorithm (ABC Algorithm). The efficacy of the EABC algorithm in this SNN is shown solving the XOR paradigm.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.