DESIGN OF THE SPIKING NEURON HAVING LEARNING CAPABILITIES BASED ON FPGA CIRCUITS

Hardware real-time implementations of Spiking Neuron Networks (SNN) are wanted for multiple applications. Introduction of the supervised learning mechanism for SNNs is a hot topic. A model of a single spiking neuron having that property is proposed. This is based on LIF simplified model. A number of design issues has been solved in order to enable the correct work of such a neuron during earning phase. The proposed extensions and modifications are described and illustrated with corresponding timing diagrams.