An embodiment of the present disclosure provides a resistive switching memory device including: a lower electrode; an amorphous metal oxide-based first active layer positioned on the lower electrode; an amorphous metal oxide-based second active layer positioned on the first active layer; and an upper electrode positioned on the second active layer, wherein the first active layer and the second active layer are made of the same substance but are different in electrical characteristic, thereby having a voluntary compliance current characteristic and a voluntary current rectification characteristic as a single device having a stable electrical characteristic, a method of manufacturing the resistive switching memory device, and an array including the resistive switching memory device.

Disclosed herein is a memory cell. The memory cell may act both as a combined selector device and memory element. The memory cell may be programmed by applying write pulses having different polarities. Different polarities of the write pulses may program different logic states into the memory cell. The memory cell may be read by read pulses all having the same polarity. The logic state of the memory cell may be detected by observing different threshold voltages when the read pulses are applied. The different threshold voltages may be responsive to the different polarities of the write pulses.

The disclosure discloses a three-dimensional (3D) convolution operation device and method based on a 3D phase change memory, which includes a 3D phase change memory, an input control module, a setting module, and an output control module. By using the 3D phase change memory to perform 3D convolution operation, the phase change units on the same bit line constitute a convolution kernel. Based on the multilayer stack structure, the upper and lower electrodes of the 3D phase change memory serve as the information input terminal, and they are convolved after passing through the respective phase change unit arrays, and the result of the convolution operation is superposed on the middle electrode in the form of current, thereby obtaining the sum of the convolution calculation results of the input information of the upper and lower electrodes, such that the 3D convolution operation is completed in one step.

The present disclosure includes apparatuses, methods, and systems for sensing two memory cells to determine multiple data values. An embodiment includes a memory having a plurality of memory cells and circuitry configured to sense memory states of each of two self-selecting multi-level memory cells (MLC) of the plurality of memory cells to determine multiple data values. The data values are determined by sensing a memory state of a first MLC using a first sensing voltage in a sense window between a first threshold voltage distribution corresponding to a first memory state and a second threshold voltage distribution corresponding to a second memory state and sensing a memory state of a second MLC using a second sensing voltage in a sense window between the first threshold voltage distribution corresponding to a first memory state and a second threshold voltage distribution corresponding to the second memory state. The sequence of determining data values includes sensing the memory state of the first and the second MLCs using higher sensing voltages than the first and the second sensing voltages in subsequent sensing windows, in repeated iterations, until the state of the first and the second MLCs are determined. The first and second sensing voltages are selectably closer in the sense window to the first threshold voltage distribution or the second threshold voltage distribution.

A semiconductor device is provided. The semiconductor device includes a substrate a substrate, a first electrode structure on the substrate, the first electrode structure including first insulating patterns and first electrode patterns, the first insulating patterns alternately stacked with the first electrode patterns, a second electrode pattern on a sidewall of the first electrode structure, and a data storage film on a sidewall of the second electrode pattern. The data storage film has a variable resistance.

A neuromorphic apparatus includes a three-dimensionally-stacked synaptic structure, and includes a plurality of unit synaptic modules, each of the plurality of unit synaptic modules including a plurality of synaptic layers, each of the plurality of synaptic layers including a plurality of stacked layers, and each of the plurality of unit synaptic modules further including a first decoder interposed between two among the plurality of synaptic layers. The neuromorphic apparatus further includes a second decoder that provides a level selection signal to the first decoder included in one among the plurality of unit synaptic modules to be accessed, and a third decoder that generates an address of one among a plurality of memristers to be accessed in a memrister array of one among the plurality of synaptic layers included in the one among the plurality of unit synaptic modules to be accessed.

This application relates to computing circuitry (200), in particular for analogue computing circuitry suitable for neuromorphic computing. The circuitry (200) has a plurality of memory cells (201), each memory cell having an input electrode (201) for receiving a cell input signal and an output (203.sub.P, 203.sub.N) for outputting a cell output signal (I.sub.P, I.sub.N), with first and second paths connecting the input electrode to the output. The cell output signal thus depends on a differential current between the first and second paths due to the cell input signal. Each memory cell also comprises at least one programmable-resistance memory element (204) in each of the first and second paths and is controllable, by selective programming of the programmable-resistance memory elements, to store a data digit that can take any of at least three different values. The plurality of memory cells are configured into one or more sets (205) of memory cells and a combiner module (206) receives the cell output signals from each of the memory cells in at least one set, and combines the cell output signals with a different scaling factor applied to each of the cell output signals.

A resistive memory device may include a first and second signal lines, a memory layer, a first and second drivers, and a first contact structure. The first signal line may include a first contact node. The first and second signal lines may intersect. The second signal line may include a second contact node. The memory layer may be at an intersecting portion between the first and second signal lines and the memory layer may be configured to change its resistance based on a voltage difference between the first and second signal lines. The first and second drivers may be configured to selectively provide the first contact node with a first power voltage and a second power voltage different from the first power voltage, respectively. The first contact structure may be configured to electrically connect the first contact node with the first and second drivers.

A neural network circuit includes a memory device in which memristors being variable resistance elements are connected in a matrix and serve as memory elements of the memory device. The neural network circuit further includes a voltage application device arranged to apply a bias voltage to the memory device and current-voltage (I-V) conversion amplification circuits arranged to convert currents flowing via the memory elements into voltages and output the voltage. A feedback resistor of a respective I-V conversion amplification circuit includes a memristor. The feedback resistor of a respective I-V conversion amplification circuit and the memory elements acting as an input resistor of the I-V conversion amplification circuit are connected to align a polarity direction of the memristor of the feedback resistor and polarity directions of the memristors of the memory elements acting as the input resistor.

Methods, systems, and devices for multi-component cell architectures for a memory device are described. A memory device may include self-selecting memory cells that include multiple self-selecting memory components (e.g., multiple layers or other segments of a self-selecting memory material, separated by electrodes). The multiple self-selecting memory components may be configured to collectively store one logic state based on the polarity of a programming pulse applied to the memory cell. The multiple memory component layers may be collectively (concurrently) programmed and read. The multiple self-selecting memory components may increase the size of a read window of the memory cell when compared to a memory cell with a single self-selecting memory component. The read window for the memory cell may correspond to the sum of the read windows of each self-selecting memory component.