Analogue Artificial Synaptic Performance of Self‐Rectifying Resistive Switching Device

The immense increase of unstructured data require novel computing systems that can process the input with low power and parallel processing. This functionality is similar to human brains are composed numerous neurons, synapses, their complex connections. To mimic brain an electronic device, resistive switching device crossbar array has attracted considerable attention for artificial synaptic devices integrated systems, respectively. For this purpose, self-rectifying cell based on Si:ZrOx thin film developed its reliability characteristics tested. Four achievements highlighted in study. 1) retention characteristic improved by adoption TaOx as oxygen reservoir layer. 2) asymmetric electrodes make (SRC) have sufficient rectifying characteristic. 3) linearity conductance update a dominant effect inference performance compared range variation. 4) interface-type shows high enough yield exhibits reliable multiply-and-accumulate operations brain-inspired system.