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...Show MoreMetadata
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.
Published in: 2018 15th International Conference on Electrical Engineering, Computing Science and Automatic Control (CCE)
Date of Conference: 05-07 September 2018
Date Added to IEEE Xplore: 15 November 2018
ISBN Information: