Abstract: Provided are a weighting device that may be driven at a low voltage and is capable of embodying multi-level weights, a neural network, and a method of operating the weighting device. The weighting device includes a switching layer that may switch between a high resistance state and a low resistance state based on a voltage applied thereto and a charge trap material layer that traps or discharges charges according to a resistance state of the switching layer. The weighting device may be used for controlling a weight in a neural network.

Abstract: Example embodiments relate to a method of fabricating a synapse memory device capable of being driven at a low voltage and realizing a multi-level memory. The synapse memory device includes a two-transistor structure in which a drain region of a first transistor including a memory layer and a first source region of a second transistor share a source-drain shared area. The synapse memory device is controlled by applying a voltage through the source-drain shared area. The memory layer includes a charge trap layer and a threshold switching layer, and may realize a non-volatile multi-level memory function.