Memristive structure of Nb/HfO_x/Pd with controllable switching mechanisms to perform featured actions in neuromorphic networks

All memristor neuromorphic networks have great potential and advantage in both technology and computational protocols for artificial intelligence. It is crucial to find suitable elementary units for both performing featured neuromorphic functions and fabrication in large scale. Here a simple memristive structure, Nb/HfO_x/Pd, is proposed for this goal. Its two resistive switching mechanisms, Mott transition of NbO₂ and oxygen vacancy (V_o) migration, can be controlled by modulating external bias directions. Negative bias activates reversible phase transition and restrains V_o filament formation to allow the memristor to mimic the firing action potential. Positive bias activates V_o filament formation and restrains the other to allow the memristor to mimic synaptic plasticity and learning protocols. The system can respond adaptively to naturally generated action potentials and modified synaptic signals from the same memristive structure. In addition, some special features related to signal encoding and recognition are discovered when the system is settled according to chaos circuit theory. Our study provides a novel approach for designing elementary units for neuromorphic computations.