Novel circuit designs of memristor synapse and neuron

In this work, novel circuits based on memristors for implementing electronic synapse and artificial neuron are designed. First, two simple synaptic circuits for implementing weighting calculations of voltage and current modes using twin memristors are proposed. A synaptic weighting operation is defined as a difference function between the twin memristors, which can be adjusted in reverse by applying programmed signals and conducting positive, zero, and negative synaptic weights. Second, two neuron circuits using the proposed memristor synapses, in which parallel computing and programming can be achieved, are designed. Finally, performances of the proposed memristor synapses and neuron circuits, such as weight programming, neuron computing, and parallel operation, are analyzed through PSpice simulations. (C) 2018 Elsevier B.V. All rightsreserved.